home.social

#strixhalo — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #strixhalo, aggregated by home.social.

fetched live
  1. GPD Win Max 3 mini gaming laptop with AMD Strix Halo to sell for $1750 and up at launch

    The GPD Win Max 3 is a mini laptop with a 9.06 inch display, an AMD Strix Halo processor with discrete-class graphics, and a design that makes it clear that this is a little PC made for both work and play. It has a keyboard large enough for touch typing, but the touchpad is above the keyboard rather than below it, and it’s squeezed between a set of game controllers.

    First unveiled earlier […]

    #gpd #gpdWin #gpdWinMax3 #handheldGamingPc #miniLaptop #strixHalo Read more: liliputing.com/gpd-win-max-3-m
  2. GPD Win Max 3 mini gaming laptop with AMD Strix Halo to sell for $1750 and up at launch

    The GPD Win Max 3 is a mini laptop with a 9.06 inch display, an AMD Strix Halo processor with discrete-class graphics, and a design that makes it clear that this is a little PC made for both work and play. It has a keyboard large enough for touch typing, but the touchpad is above the keyboard rather than below it, and it’s squeezed between a set of game controllers.

    First unveiled earlier […]

    #gpd #gpdWin #gpdWinMax3 #handheldGamingPc #miniLaptop #strixHalo Read more: liliputing.com/gpd-win-max-3-m
  3. GPD Win Max 3 mini gaming laptop with AMD Strix Halo to sell for $1750 and up at launch

    The GPD Win Max 3 is a mini laptop with a 9.06 inch display, an AMD Strix Halo processor with discrete-class graphics, and a design that makes it clear that this is a little PC made for both work and play. It has a keyboard large enough for touch typing, but the touchpad is above the keyboard rather than below it, and it’s squeezed between a set of game controllers.

    First unveiled earlier […]

    #gpd #gpdWin #gpdWinMax3 #handheldGamingPc #miniLaptop #strixHalo Read more: liliputing.com/gpd-win-max-3-m
  4. GPD Win Max 3 mini gaming laptop with AMD Strix Halo to sell for $1750 and up at launch

    The GPD Win Max 3 is a mini laptop with a 9.06 inch display, an AMD Strix Halo processor with discrete-class graphics, and a design that makes it clear that this is a little PC made for both work and play. It has a keyboard large enough for touch typing, but the touchpad is above the keyboard rather than below it, and it’s squeezed between a set of game controllers.

    First unveiled earlier […]

    #gpd #gpdWin #gpdWinMax3 #handheldGamingPc #miniLaptop #strixHalo Read more: liliputing.com/gpd-win-max-3-m
  5. 🧪 LLM Benchmark Showdown: 5 lokale Ollama-Modelle im Vergleich

    Getestet auf derselben Hardware (#gmktecevo2 ):
    (100 Samples) — Math
    (100/Kategorie) — Function Calling
    + (50) — Python Coding
    + (20) — Python Coding

    📊 Ergebnisse (Accuracy / Output TK/s / VRAM):

    **qwen3.8:27b**
    GSM8K 82% | BFCL 91.5% | MBPP+ 100% | HE+ 100%
    ⚡ 25.5 TK/s | 💾 18 GB VRAM

    **qwen3.6:27b**
    GSM8K 83% | BFCL 93% | MBPP+ 98% | HE+ 75%
    ⚡ 12.7 TK/s | 💾 33 GB VRAM

    **qwen3.6:35b**
    GSM8K 84% | BFCL 90% | MBPP+ 98% | HE+ 55%
    ⚡ 61.8 TK/s | 💾 27 GB VRAM

    **ornith-1.5:35b**
    GSM8K 75% | BFCL 92.5% | MBPP+ 78% | HE+ 0%
    ⚡ 63.6 TK/s | 💾 26 GB VRAM

    **nemotron-3.5-lightning:30b**
    GSM8K 59% | BFCL 74% | MBPP+ 94% | HE+ 0%
    ⚡ 91.9 TK/s | 💾 26 GB VRAM

    🏆 Fazit:

    qwen3.8:27b ist der klare Sieger — als einziges Modell 100% bei beiden Coding-Benchmarks, bei GSM8K/BFCL gleichauf mit den anderen Qwen-Modellen. Bei 25.5 TK/s und nur 18 GB VRAM das beste Qualität/Speed/Effizienz-Verhältnis.

    qwen3.6:27b ist qualitativ nah dran (BFCL sogar 93%), aber mit 12.7 TK/s unerträglich langsam und frisst 33 GB VRAM — fast 2× so viel wie qwen3.8 bei halber Speed.

    qwen3.6:35b ist mit 61.8 TK/s 2.4× schneller als qwen3.8, aber HE+ nur 55% (vs 100%). Trading Code-Qualität für Speed.

    ornith-1.5:35b und nemotron-3.5-lightning:30b fallen bei Coding komplett durch (HE+ 0%), sind aber die schnellsten Modelle im Feld (64 / 92 TK/s).

    💡 TK/s = generierte Tokens/Sekunde (Warm-Run, ollama --verbose).
    💾 VRAM = GPU-Speicher bei max context (262K bzw. 1M bei nemotron).

  6. I am installing Pangolin as replacement to Cloudflare tunnels. I'm having some trouble configuring Traefik middlewares, and decided to ask advise from new Qwen3.8. It answered pretty quickly, did some net searches, and gave helpful answer. What's amazing is that it runs locally in an AMD Strix Halo mini-pc. I don't need any AI sub because the Ai is just another service in a mini-pc I am using anyway.

    I got forward with Pangolin, and gave now e.g. Crowdsec completely integrated via Traefik plugin.

    Now I'm stuck with Traefik Middleware Manager. It should allow me to pick a service (a web server) and hook in required Middleware. But it has hardly any documentation. I have installed a set of plugins, but I'm puzzled how to add and configure them into middlewares for a service. I guess I need to read the truth from sources😅.
    #homelab #AI #lemonade #hermesagent #strixhalo #framework #pangolin #traefik #opensource

  7. I am installing Pangolin as replacement to Cloudflare tunnels. I'm having some trouble configuring Traefik middlewares, and decided to ask advise from new Qwen3.8. It answered pretty quickly, did some net searches, and gave helpful answer. What's amazing is that it runs locally in an AMD Strix Halo mini-pc. I don't need any AI sub because the Ai is just another service in a mini-pc I am using anyway.

    I got forward with Pangolin, and gave now e.g. Crowdsec completely integrated via Traefik plugin.

    Now I'm stuck with Traefik Middleware Manager. It should allow me to pick a service (a web server) and hook in required Middleware. But it has hardly any documentation. I have installed a set of plugins, but I'm puzzled how to add and configure them into middlewares for a service. I guess I need to read the truth from sources😅.
    #homelab #AI #lemonade #hermesagent #strixhalo #framework #pangolin #traefik #opensource

  8. I am installing Pangolin as replacement to Cloudflare tunnels. I'm having some trouble configuring Traefik middlewares, and decided to ask advise from new Qwen3.8. It answered pretty quickly, did some net searches, and gave helpful answer. What's amazing is that it runs locally in an AMD Strix Halo mini-pc. I don't need any AI sub because the Ai is just another service in a mini-pc I am using anyway.

    I got forward with Pangolin, and gave now e.g. Crowdsec completely integrated via Traefik plugin.

    Now I'm stuck with Traefik Middleware Manager. It should allow me to pick a service (a web server) and hook in required Middleware. But it has hardly any documentation. I have installed a set of plugins, but I'm puzzled how to add and configure them into middlewares for a service. I guess I need to read the truth from sources😅.
    #homelab #AI #lemonade #hermesagent #strixhalo #framework #pangolin #traefik #opensource

  9. I am installing Pangolin as replacement to Cloudflare tunnels. I'm having some trouble configuring Traefik middlewares, and decided to ask advise from new Qwen3.8. It answered pretty quickly, did some net searches, and gave helpful answer. What's amazing is that it runs locally in an AMD Strix Halo mini-pc. I don't need any AI sub because the Ai is just another service in a mini-pc I am using anyway.

    I got forward with Pangolin, and gave now e.g. Crowdsec completely integrated via Traefik plugin.

    Now I'm stuck with Traefik Middleware Manager. It should allow me to pick a service (a web server) and hook in required Middleware. But it has hardly any documentation. I have installed a set of plugins, but I'm puzzled how to add and configure them into middlewares for a service. I guess I need to read the truth from sources😅.
    #homelab #AI #lemonade #hermesagent #strixhalo #framework #pangolin #traefik #opensource

  10. I am installing Pangolin as replacement to Cloudflare tunnels. I'm having some trouble configuring Traefik middlewares, and decided to ask advise from new Qwen3.8. It answered pretty quickly, did some net searches, and gave helpful answer. What's amazing is that it runs locally in an AMD Strix Halo mini-pc. I don't need any AI sub because the Ai is just another service in a mini-pc I am using anyway.

    I got forward with Pangolin, and gave now e.g. Crowdsec completely integrated via Traefik plugin.

    Now I'm stuck with Traefik Middleware Manager. It should allow me to pick a service (a web server) and hook in required Middleware. But it has hardly any documentation. I have installed a set of plugins, but I'm puzzled how to add and configure them into middlewares for a service. I guess I need to read the truth from sources😅.

  11. ich benchmarke grade ein paar llms auf meinem mit 200 GSM8K + 3×100 BFCL Samples

    dabei ist mir aufgefallen das thinking moodelle wie qwen 3.6 0% ergebnis liefert - wegen zu langen thinking blocks

    da in das thinking drin ist - ist das doppelt... und hat deshalb bei mir bei qwen3.6 immer wieder geloopt und war unbrauchbar

    offensichtlicher unterschied: qwen3.8 hat thinking nicht aktiv! also ist das der gamechanger???

    hier einschätzung
    Thinking-Modelle in Agent-Loops: Das Problem
    Die Recherche bestätigt unsere Benchmark-Ergebnisse eins zu eins:

    1. Token-Budget wird im Agent-Loop multipliziert, nicht addiert
    - Ein einzelner Query kostet mit Standard-Modell ~7 Tokens, mit Thinking-Modell ~255-603 Tokens
    - In einem Agent-Loop mit 12 Iterationen zahlst du nicht 10x — du zahlst 10x × 12, und das wird bei jeder Iteration durch die wachsende History weiter amplifiziert
    - Eine 10-Turn-Loop sendet ~50x mehr Tokens als ein einzelner linearer Call (Falconer Guides)

    2. Thinking-Blöcke fressen genau das, was der Agent am dringendsten braucht: Context
    - Stanford Digital Economy Lab: Agent-Tasks brauchen ~1000x mehr Tokens als Chat, mit 30x Variance
    - Thinking-Output wird zur History hinzugefügt → bei jedem Turn ist mehr Context belegt → das eigentliche Task-Wissen wird verdrängt → schlechtere Ergebnisse
    - Genau das haben wir gesehen: qwen3.6:35b mit Thinking = 1.5% GSM8K (fast alles leer), ohne Thinking = 100% auf 5 Samples

    3. Reasoning-Loops sind ein echtes, beobachtetes Phänomen
    - Ein dokumentierter Fall: ein Agent machte 847 Reasoning-Steps und lieferte nie ein Ergebnis (dev.to)
    - "Overthinking leads to poor decisions" — jede zusätzliche Reasoning-Step macht es schlimmer, nicht besser
    - Agent ruft dieselbe API 14x hintereinander, "nur noch ein Schritt mehr" wird das Ergebnis schon perfekt machen (ShopClawMart)

    4. Reasoning bei reinen Action-Knoten ist reine Verschwendung

    "Once a plan is formed and the current step is 'call the search API with this query' or 'write this string to that file,' reasoning tokens add nothing. The action is deterministic. A fast model will generate the correct function call as reliably as a reasoning model at a fraction of the cost. This is the most common budget leak in agent systems."

    Was das für Hermes bedeutet
    In einem Agent-System wie Hermes ist die Situation noch verschärft:
    - Jeder Tool-Call erzeugt Output, der zur History kommt
    - Der Context füllt sich ohnehin schon schnell (System-Prompt, Skills, Tool-Outputs...)
    - Kommt jetzt noch ein 2000-Token Thinking-Block pro Turn dazu, ist der Context nach 5-6 Turns voll — und dann beginnt der Context-Overflow: ältere Task-Infos fallen raus, der Agent verliert den Faden, fängt an zu loopen
    - Das ist auch warum du ja gesagt hast "Context fills up fast" in Hermes — Thinking würde das dramatisch verschlimmern

    1/x

  12. We tested the Bosgame M5, an AMD Ryzen AI Max+ 395 system that is one of the lowest cost 128GB LPDDR5X local AI systems out there#amd #AMDRyzen #Bosgame #RyzenAI #StrixHalo
    Bosgame M5 AMD Ryzen AI Max+ 395 128GB AI Desktop Review
  13. We tested the Bosgame M5, an AMD Ryzen AI Max+ 395 system that is one of the lowest cost 128GB LPDDR5X local AI systems out there#amd #AMDRyzen #Bosgame #RyzenAI #StrixHalo
    Bosgame M5 AMD Ryzen AI Max+ 395 128GB AI Desktop Review
  14. geizhals.de/gmktec-evo-x2-a348

    Eben den hier auf Amazon gekauft 🙈 der Gewinn aus finanziert mit den

    SSD heatsink bestellt
    Firmware Update zuerst angehen (gibt es Updates die Abstürze verhindern sollen) - unter Linux schwierig

    Dann geht es ab

    Warum nur 64gb? Die letzten Monate kam nichts neue raus in 120b Größe - denke wenn LLM rauskommen in nächsten Zeit dann 30b große - wie jetzt qwen3.8

    Dann kann man 16gb für Ubuntu geben und 48gb für LLM --- dann ist man gut aufgestellt

    i am coming Back 😁

  15. RT @TeksEdge: 🔥 Besitzer von Strix Halo 👉 Ihr habt einen weiteren lokalen KI-Beschleuniger in eurem Rechner, der ungenutzt bleibt. AMDs FastFlowLM kann unterstützte Modelle vollständig auf dem Ryzen AI XDNA2 NPU ausführen, ohne die Radeon-GPU zu nutzen. FastFlowLM ist wie Ollama, wurde aber speziell für AMDs NPU entwickelt. 👀 ⚡ LLMs 👁️ Vision 🎙️ Audio 🧩 Embeddings 🧠 MoE 📚 Bis zu 256K Kontext 🔋 Bis zu 10×+ Energieeffizienz 🪶 ~16MB Laufzeitzeit Unterstützte Ryzen AI-Chips umfassen: ✅ Strix Halo ✅ Strix Point ✅ Kraken Point ✅ Gorgon Point Euer Strix Halo verfügt bereits über: 🧠 CPU 🎮 Radeon 8060S GPU ⚡ XDNA2 NPU Die meisten lokalen KI-Arbeitslasten belasten die GPU und ignorieren die NPU weitgehend. Jetzt könntet ihr folgendes tun: ⚡ NPU → kleine LLM-/Vision-/Sprach-Arbeitslast 🎮 GPU → große lokale LLMs Derselbe PC. Zwei unabhängige KI-Beschleuniger arbeiten gleichzeitig. 🎯 Strix Halo ist nicht nur eine 128GB-Box mit einheitlichem GPU-Speicher. Dieser NPU wird zunehmend zu nützlicher KI-Hardware für den lokalen Einsatz.

    mehr auf Arint.info

    #AMD #FastFlowLM #LocalAI #NPU #RyzenAI #StrixHalo #arint_info

    https://x.com/TeksEdge/status/2087335758231122143#m

  16. RT @TeksEdge: 🔥 Besitzer von Strix Halo 👉 Ihr habt einen weiteren lokalen KI-Beschleuniger in eurem Rechner, der ungenutzt bleibt. AMDs FastFlowLM kann unterstützte Modelle vollständig auf dem Ryzen AI XDNA2 NPU ausführen, ohne die Radeon-GPU zu nutzen. FastFlowLM ist wie Ollama, wurde aber speziell für AMDs NPU entwickelt. 👀 ⚡ LLMs 👁️ Vision 🎙️ Audio 🧩 Embeddings 🧠 MoE 📚 Bis zu 256K Kontext 🔋 Bis zu 10×+ Energieeffizienz 🪶 ~16MB Laufzeitzeit Unterstützte Ryzen AI-Chips umfassen: ✅ Strix Halo ✅ Strix Point ✅ Kraken Point ✅ Gorgon Point Euer Strix Halo verfügt bereits über: 🧠 CPU 🎮 Radeon 8060S GPU ⚡ XDNA2 NPU Die meisten lokalen KI-Arbeitslasten belasten die GPU und ignorieren die NPU weitgehend. Jetzt könntet ihr folgendes tun: ⚡ NPU → kleine LLM-/Vision-/Sprach-Arbeitslast 🎮 GPU → große lokale LLMs Derselbe PC. Zwei unabhängige KI-Beschleuniger arbeiten gleichzeitig. 🎯 Strix Halo ist nicht nur eine 128GB-Box mit einheitlichem GPU-Speicher. Dieser NPU wird zunehmend zu nützlicher KI-Hardware für den lokalen Einsatz.

    mehr auf Arint.info

    #AMD #FastFlowLM #LocalAI #NPU #RyzenAI #StrixHalo #arint_info

    https://x.com/TeksEdge/status/2087335758231122143#m

  17. RT @TeksEdge: 🔥 Besitzer von Strix Halo 👉 Ihr habt einen weiteren lokalen KI-Beschleuniger in eurem Rechner, der ungenutzt bleibt. AMDs FastFlowLM kann unterstützte Modelle vollständig auf dem Ryzen AI XDNA2 NPU ausführen, ohne die Radeon-GPU zu nutzen. FastFlowLM ist wie Ollama, wurde aber speziell für AMDs NPU entwickelt. 👀 ⚡ LLMs 👁️ Vision 🎙️ Audio 🧩 Embeddings 🧠 MoE 📚 Bis zu 256K Kontext 🔋 Bis zu 10×+ Energieeffizienz 🪶 ~16MB Laufzeitzeit Unterstützte Ryzen AI-Chips umfassen: ✅ Strix Halo ✅ Strix Point ✅ Kraken Point ✅ Gorgon Point Euer Strix Halo verfügt bereits über: 🧠 CPU 🎮 Radeon 8060S GPU ⚡ XDNA2 NPU Die meisten lokalen KI-Arbeitslasten belasten die GPU und ignorieren die NPU weitgehend. Jetzt könntet ihr folgendes tun: ⚡ NPU → kleine LLM-/Vision-/Sprach-Arbeitslast 🎮 GPU → große lokale LLMs Derselbe PC. Zwei unabhängige KI-Beschleuniger arbeiten gleichzeitig. 🎯 Strix Halo ist nicht nur eine 128GB-Box mit einheitlichem GPU-Speicher. Dieser NPU wird zunehmend zu nützlicher KI-Hardware für den lokalen Einsatz.

    mehr auf Arint.info

    #AMD #FastFlowLM #LocalAI #NPU #RyzenAI #StrixHalo #arint_info

    https://x.com/TeksEdge/status/2087335758231122143#m

  18. RT @TeksEdge: 🔥 Besitzer von Strix Halo 👉 ihr habt einen weiteren Local-AI-Beschleuniger in eurem Rechner, der ungenutzt bleibt. AMDs FastFlowLM kann unterstützte Modelle vollständig auf dem Ryzen AI XDNA2-NPU ausführen, ohne die Radeon-GPU zu nutzen. FastFlowLM funktioniert ähnlich wie Ollama, ist jedoch speziell für AMDs NPU entwickelt. 👀 ⚡ LLMs 👁️ Vision 🎙️ Audio 🧩 Embeddings 🧠 MoE 📚 Bis zu 256K Kontext 🔋 Bis zu 10×+ Energieeffizienz 🪶 ~16MB Laufzeitzeit Unterstützte Ryzen AI-Chips umfassen: ✅ Strix Halo ✅ Strix Point ✅ Kraken Point ✅ Gorgon Point Euer Strix Halo verfügt bereits über: 🧠 CPU 🎮 Radeon 8060S-GPU ⚡ XDNA2-NPU Die meisten Local-AI-Workloads belasten die GPU und ignorieren die NPU weitgehend. Jetzt könnt ihr potenziell Folgendes tun: ⚡ NPU → kleine LLM-/Vision-/Sprach-Workloads 🎮 GPU → große lokale LLMs Derselbe PC. Zwei unabhängige KI-Beschleuniger arbeiten gleichzeitig. 🎯 Strix Halo ist nicht nur eine 128GB-Box mit einheitlichem GPU-Speicher. Dieser NPU wird nun auch als nützliche KI-Hardware für den lokalen Einsatz relevant.

    mehr auf Arint.info

    #AMD #FastFlowLM #LocalAI #NPU #RyzenAI #StrixHalo #arint_info

    https://x.com/TeksEdge/status/2087335758231122143#m

  19. RT @TeksEdge: 🔥 Besitzer von Strix Halo 👉 ihr habt einen weiteren Local-AI-Beschleuniger in eurem Rechner, der ungenutzt bleibt. AMDs FastFlowLM kann unterstützte Modelle vollständig auf dem Ryzen AI XDNA2-NPU ausführen, ohne die Radeon-GPU zu nutzen. FastFlowLM funktioniert ähnlich wie Ollama, ist jedoch speziell für AMDs NPU entwickelt. 👀 ⚡ LLMs 👁️ Vision 🎙️ Audio 🧩 Embeddings 🧠 MoE 📚 Bis zu 256K Kontext 🔋 Bis zu 10×+ Energieeffizienz 🪶 ~16MB Laufzeitzeit Unterstützte Ryzen AI-Chips umfassen: ✅ Strix Halo ✅ Strix Point ✅ Kraken Point ✅ Gorgon Point Euer Strix Halo verfügt bereits über: 🧠 CPU 🎮 Radeon 8060S-GPU ⚡ XDNA2-NPU Die meisten Local-AI-Workloads belasten die GPU und ignorieren die NPU weitgehend. Jetzt könnt ihr potenziell Folgendes tun: ⚡ NPU → kleine LLM-/Vision-/Sprach-Workloads 🎮 GPU → große lokale LLMs Derselbe PC. Zwei unabhängige KI-Beschleuniger arbeiten gleichzeitig. 🎯 Strix Halo ist nicht nur eine 128GB-Box mit einheitlichem GPU-Speicher. Dieser NPU wird nun auch als nützliche KI-Hardware für den lokalen Einsatz relevant.

    mehr auf Arint.info

    #AMD #FastFlowLM #LocalAI #NPU #RyzenAI #StrixHalo #arint_info

    https://x.com/TeksEdge/status/2087335758231122143#m

  20. RT @TeksEdge: 🔥 Besitzer von Strix Halo 👉 ihr habt einen weiteren Local-AI-Beschleuniger in eurem Rechner, der ungenutzt bleibt. AMDs FastFlowLM kann unterstützte Modelle vollständig auf dem Ryzen AI XDNA2-NPU ausführen, ohne die Radeon-GPU zu nutzen. FastFlowLM funktioniert ähnlich wie Ollama, ist jedoch speziell für AMDs NPU entwickelt. 👀 ⚡ LLMs 👁️ Vision 🎙️ Audio 🧩 Embeddings 🧠 MoE 📚 Bis zu 256K Kontext 🔋 Bis zu 10×+ Energieeffizienz 🪶 ~16MB Laufzeitzeit Unterstützte Ryzen AI-Chips umfassen: ✅ Strix Halo ✅ Strix Point ✅ Kraken Point ✅ Gorgon Point Euer Strix Halo verfügt bereits über: 🧠 CPU 🎮 Radeon 8060S-GPU ⚡ XDNA2-NPU Die meisten Local-AI-Workloads belasten die GPU und ignorieren die NPU weitgehend. Jetzt könnt ihr potenziell Folgendes tun: ⚡ NPU → kleine LLM-/Vision-/Sprach-Workloads 🎮 GPU → große lokale LLMs Derselbe PC. Zwei unabhängige KI-Beschleuniger arbeiten gleichzeitig. 🎯 Strix Halo ist nicht nur eine 128GB-Box mit einheitlichem GPU-Speicher. Dieser NPU wird nun auch als nützliche KI-Hardware für den lokalen Einsatz relevant.

    mehr auf Arint.info

    #AMD #FastFlowLM #LocalAI #NPU #RyzenAI #StrixHalo #arint_info

    https://x.com/TeksEdge/status/2087335758231122143#m

  21. We review the Minisforum N5 Max, a 64GB AMD Strix Halo system that combines 10GbE, a 5-bay NAS, and more into a single box#amd #Minisforum #nas #StrixHalo
    Minisforum N5 Max Review with AMD Ryzen AI Max+ 395
  22. We review the Minisforum N5 Max, a 64GB AMD Strix Halo system that combines 10GbE, a 5-bay NAS, and more into a single box#amd #Minisforum #nas #StrixHalo
    Minisforum N5 Max Review with AMD Ryzen AI Max+ 395
  23. We review the Minisforum N5 Max, a 64GB AMD Strix Halo system that combines 10GbE, a 5-bay NAS, and more into a single box#amd #Minisforum #nas #StrixHalo
    Minisforum N5 Max Review with AMD Ryzen AI Max+ 395
  24. ACEMAGIC F9A is an upcoming mini PC with a 2 liter aluminum body and AMD Ryzen AI Max+ inside with up to 128GB LPDDR5x-8000 memory, two SSDs, OCuLink, USB4, and integrated mics and speakers. #ACEMAGIC #ACEMAGICF9A #MiniPC #StrixHalo acemagic.com/products/acemagic

  25. ACEMAGIC F9A is an upcoming mini PC with a 2 liter aluminum body and AMD Ryzen AI Max+ inside with up to 128GB LPDDR5x-8000 memory, two SSDs, OCuLink, USB4, and integrated mics and speakers. acemagic.com/products/acemagic

  26. ACEMAGIC F9A is an upcoming mini PC with a 2 liter aluminum body and AMD Ryzen AI Max+ inside with up to 128GB LPDDR5x-8000 memory, two SSDs, OCuLink, USB4, and integrated mics and speakers. #ACEMAGIC #ACEMAGICF9A #MiniPC #StrixHalo acemagic.com/products/acemagic

  27. ACEMAGIC F9A is an upcoming mini PC with a 2 liter aluminum body and AMD Ryzen AI Max+ inside with up to 128GB LPDDR5x-8000 memory, two SSDs, OCuLink, USB4, and integrated mics and speakers. #ACEMAGIC #ACEMAGICF9A #MiniPC #StrixHalo acemagic.com/products/acemagic

  28. ACEMAGIC F9A is an upcoming mini PC with a 2 liter aluminum body and AMD Ryzen AI Max+ inside with up to 128GB LPDDR5x-8000 memory, two SSDs, OCuLink, USB4, and integrated mics and speakers. #ACEMAGIC #ACEMAGICF9A #MiniPC #StrixHalo acemagic.com/products/acemagic

  29. More AI news from AMD, re-use of the better parts of their Strix Halo yield for industrial use cases.

    "Physical AI" aka robotics and edge use cases. Buzzword galore! 😆

    Still remember when "edge" was the new buzzword Pepperidge Farm Remembers

    servethehome.com/amds-physical

    Something I do find interesting is the claim of hard real-time assurances whilst virtualized with Xen.

    Technically a guaranteed deadline of 2 years is hard real-time too, just as MS-DOS is an amazing real-time OS, but I'm sure that's not what they're talking about...

    Any one got more info on the Xen claim? Haven't heard so much about them these days...

    #amd #strixhalo #ai #EmbedddedSystems #PhysicalAI #edgecomputing #robotics #xen #virtualization #realtime

  30. More AI news from AMD, re-use of the better parts of their Strix Halo yield for industrial use cases.

    servethehome.com/amds-physical

    "Physical AI" aka robotics and edge use cases. Buzzword galore! 😆
    Still remember when "edge" was the new buzzword Pepperidge Farm Remembers

    Something I do find interesting is the claim of hard real-time assurances whilst virtualized with Xen.

    Technically a guaranteed deadline of 2 years is hard real-time too, just as MS-DOS is an amazing real-time OS, but I'm sure that's not what they're talking about...

    Any one got more info on the Xen claim? Haven't heard so much about them these days...

    #amd #strixhalo #ai #EmbedddedSystems #PhysicalAI #edgecomputing #robotics #xen #virtualization #realtime #rtos #msdos

  31. More AI news from AMD, re-use of the better parts of their Strix Halo yield for industrial use cases.

    "Physical AI" aka robotics and edge use cases. Buzzword galore! 😆

    Still remember when "edge" was the new buzzword Pepperidge Farm Remembers

    servethehome.com/amds-physical

    Something I do find interesting is the claim of hard real-time assurances whilst virtualized with Xen.

    Technically a guaranteed deadline of 2 years is hard real-time too, just as MS-DOS is an amazing real-time OS, but I'm sure that's not what they're talking about...

    Any one got more info on the Xen claim? Haven't heard so much about them these days...

    #amd #strixhalo #ai #EmbedddedSystems #PhysicalAI #edgecomputing #robotics #xen #virtualization #realtime

  32. More AI news from AMD, re-use of the better parts of their Strix Halo yield for industrial use cases.

    "Physical AI" aka robotics and edge use cases. Buzzword galore! 😆

    Still remember when "edge" was the new buzzword Pepperidge Farm Remembers

    servethehome.com/amds-physical

    Something I do find interesting is the claim of hard real-time assurances whilst virtualized with Xen.

    Technically a guaranteed deadline of 2 years is hard real-time too, just as MS-DOS is an amazing real-time OS, but I'm sure that's not what they're talking about...

    Any one got more info on the Xen claim? Haven't heard so much about them these days...

    #amd #strixhalo #ai #EmbedddedSystems #PhysicalAI #edgecomputing #robotics #xen #virtualization #realtime

  33. More AI news from AMD, re-use of the better parts of their Strix Halo yield for industrial use cases.

    "Physical AI" aka robotics and edge use cases. Buzzword galore! 😆

    Still remember when "edge" was the new buzzword Pepperidge Farm Remembers

    servethehome.com/amds-physical

    Something I do find interesting is the claim of hard real-time assurances whilst virtualized with Xen.

    Technically a guaranteed deadline of 2 years is hard real-time too, just as MS-DOS is an amazing real-time OS, but I'm sure that's not what they're talking about...

    Any one got more info on the Xen claim? Haven't heard so much about them these days...

    #amd #strixhalo #ai #EmbedddedSystems #PhysicalAI #edgecomputing #robotics #xen #virtualization #realtime

  34. AMD’s Physical AI Plans Come Into Focus as Company Launches Ryzen Embedded AI X100

    At Advancing AI 2026, AMD laid out their plans for a comprehensive product stack for physical AI hardware. From SoCs to modules to dev kits, AMD is eyeing physical AI as their next big growth opportunity#amd #Edge #Kria #PhysicalAI #RDNA35 #RyzenEmbedded #StrixHalo #Zen5
    AMD's Physical AI Plans Come Into Focus as Company Launches Ryzen Embedded AI X100

  35. Being now retired I no longer have corporate AI budget to spend. So I tried local LLM in AMD Halo Strix PC, a Framework Desktop. I did try earlier when it was new, but was *not impressed*. Now, after a year or so, much has changed. Models don't crash all the time, less hallucinations, and faster. I have now settled to Lemonade server and Hermes Agent in Hermes Studio, might delete later.

    I think I'm onto something with this. As a first project I configured it into blind UI using only voice. I can walk around with wireless headset, ask AI to search something. STT model turns it to text, chat model thinks, Kagi MCP does the web searches, and TTS model speaks out the answer. All this in a regular mini PC.

    Next I probably need to look at open source coding tools. Hmm, blind coding in the garden, eh? FYI I'm not blind, just tinkering with ideas.

  36. Yeah this is the model I have been wanting for my #StrixHalo since I got it. Perfect.

  37. Yeah this is the model I have been wanting for my #StrixHalo since I got it. Perfect.

  38. Два AMD Strix Halo в AI‑инфраструктуре: 34 контейнера на одном, ~70 tok/s Qwen3.6 на другом

    На узле моей AI‑платформы крутятся 34 контейнера: Dify, RAGFlow, векторные базы, мониторинг и SSO. Большой языковой модели среди них нет: основную генерацию стек получает по LAN с DGX Spark. На втором таком же мини‑ПК я отдельно поднял локальную Qwen3.6–35B‑A3B и прогнал серию замеров от 1K до 64K при контекстном окне 256K. Обе машины — Beelink GTR9 Pro на Ryzen AI Max+ 395 (Strix Halo). Ниже — что эти коробки реально умеют: 117,4 ГиБ GTT после настройки ttm.pages_limit , p50/p95 локальных эмбеддингов и реранка, около 70 tok/s генерации через Vulkan/RADV и три грабли gfx1151.

    habr.com/ru/articles/1058502/

    #strixhalo #amd #selfhosted #llm #vulkan #rocm

  39. Два AMD Strix Halo в AI‑инфраструктуре: 34 контейнера на одном, ~70 tok/s Qwen3.6 на другом

    На узле моей AI‑платформы крутятся 34 контейнера: Dify, RAGFlow, векторные базы, мониторинг и SSO. Большой языковой модели среди них нет: основную генерацию стек получает по LAN с DGX Spark. На втором таком же мини‑ПК я отдельно поднял локальную Qwen3.6–35B‑A3B и прогнал серию замеров от 1K до 64K при контекстном окне 256K. Обе машины — Beelink GTR9 Pro на Ryzen AI Max+ 395 (Strix Halo). Ниже — что эти коробки реально умеют: 117,4 ГиБ GTT после настройки ttm.pages_limit , p50/p95 локальных эмбеддингов и реранка, около 70 tok/s генерации через Vulkan/RADV и три грабли gfx1151.

    habr.com/ru/articles/1058502/

    #strixhalo #amd #selfhosted #llm #vulkan #rocm

  40. Два AMD Strix Halo в AI‑инфраструктуре: 34 контейнера на одном, ~70 tok/s Qwen3.6 на другом

    На узле моей AI‑платформы крутятся 34 контейнера: Dify, RAGFlow, векторные базы, мониторинг и SSO. Большой языковой модели среди них нет: основную генерацию стек получает по LAN с DGX Spark. На втором таком же мини‑ПК я отдельно поднял локальную Qwen3.6–35B‑A3B и прогнал серию замеров от 1K до 64K при контекстном окне 256K. Обе машины — Beelink GTR9 Pro на Ryzen AI Max+ 395 (Strix Halo). Ниже — что эти коробки реально умеют: 117,4 ГиБ GTT после настройки ttm.pages_limit , p50/p95 локальных эмбеддингов и реранка, около 70 tok/s генерации через Vulkan/RADV и три грабли gfx1151.

    habr.com/ru/articles/1058502/

    #strixhalo #amd #selfhosted #llm #vulkan #rocm

  41. Come Scegliere il Miglior Mini PC per l'AI Locale nel 2026: Strix Halo vs DGX Spark vs Mac

    Un mini PC grande quanto un libro tascabile è oggi in grado di eseguire localmente un modello da 200 miliardi di parametri. Ma la scelta non dipende solo dal prezzo. La capacità della memoria determina quali modelli possono essere caricati, la larghezza di banda influisce sulla velocità di esecuzione e lo stack software — CUDA, ROCm o Metal — stabilisce se gli strumenti che utilizi funzioneranno davvero. Ecco un confronto tra le quattro principali opzioni disponibili nel 2026, con prezzi e benchmark aggiornati.

    buysellram.com/blog/how-to-cho…

    #AIlocale #LLM #MiniPC #HardwareAI #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #InfrastrutturaAI #Ollama #RyzenAI #AIPC #AMD #NVIDIA #Apple

  42. Come Scegliere il Miglior Mini PC per l'AI Locale nel 2026: Strix Halo vs DGX Spark vs Mac

    Un mini PC grande quanto un libro tascabile è oggi in grado di eseguire localmente un modello da 200 miliardi di parametri. Ma la scelta non dipende solo dal prezzo. La capacità della memoria determina quali modelli possono essere caricati, la larghezza di banda influisce sulla velocità di esecuzione e lo stack software — CUDA, ROCm o Metal — stabilisce se gli strumenti che utilizi funzioneranno davvero. Ecco un confronto tra le quattro principali opzioni disponibili nel 2026, con prezzi e benchmark aggiornati.

    buysellram.com/blog/how-to-cho…

    #AIlocale #LLM #MiniPC #HardwareAI #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #InfrastrutturaAI #Ollama #RyzenAI #AIPC #AMD #NVIDIA #Apple

  43. Come Scegliere il Miglior Mini PC per l'AI Locale nel 2026: Strix Halo vs DGX Spark vs Mac

    Un mini PC grande quanto un libro tascabile è oggi in grado di eseguire localmente un modello da 200 miliardi di parametri. Ma la scelta non dipende solo dal prezzo. La capacità della memoria determina quali modelli possono essere caricati, la larghezza di banda influisce sulla velocità di esecuzione e lo stack software — CUDA, ROCm o Metal — stabilisce se gli strumenti che utilizi funzioneranno davvero. Ecco un confronto tra le quattro principali opzioni disponibili nel 2026, con prezzi e benchmark aggiornati.

    buysellram.com/blog/how-to-cho…

    #AIlocale #LLM #MiniPC #HardwareAI #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #InfrastrutturaAI #Ollama #RyzenAI #AIPC #AMD #NVIDIA #Apple

  44. Come Scegliere il Miglior Mini PC per l'AI Locale nel 2026: Strix Halo vs DGX Spark vs Mac

    Un mini PC grande quanto un libro tascabile è oggi in grado di eseguire localmente un modello da 200 miliardi di parametri. Ma la scelta non dipende solo dal prezzo. La capacità della memoria determina quali modelli possono essere caricati, la larghezza di banda influisce sulla velocità di esecuzione e lo stack software — CUDA, ROCm o Metal — stabilisce se gli strumenti che utilizi funzioneranno davvero. Ecco un confronto tra le quattro principali opzioni disponibili nel 2026, con prezzi e benchmark aggiornati.

    buysellram.com/blog/how-to-cho…

    #AIlocale #LLM #MiniPC #HardwareAI #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #InfrastrutturaAI #Ollama #RyzenAI #AIPC #AMD #NVIDIA #Apple

  45. Come Scegliere il Miglior Mini PC per l'AI Locale nel 2026: Strix Halo vs DGX Spark vs Mac

    Un mini PC grande quanto un libro tascabile è oggi in grado di eseguire localmente un modello da 200 miliardi di parametri. Ma la scelta non dipende solo dal prezzo. La capacità della memoria determina quali modelli possono essere caricati, la larghezza di banda influisce sulla velocità di esecuzione e lo stack software — CUDA, ROCm o Metal — stabilisce se gli strumenti che utilizi funzioneranno davvero. Ecco un confronto tra le quattro principali opzioni disponibili nel 2026, con prezzi e benchmark aggiornati.

    buysellram.com/blog/how-to-cho…

    #AIlocale #LLM #MiniPC #HardwareAI #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #InfrastrutturaAI #Ollama #RyzenAI #AIPC #AMD #NVIDIA #Apple

  46. Lilbits: Flipper Zero’s firmware future, a new Linux gaming laptop, an E Ink monitor, and AMD’s pricey Ryzen Halo mini PC

    Shortly after launching a new thin and light Linux laptop with an Intel Panther Lake processor, Linux PC company System76 is preparing to launch… another notebook that could be described the same way.

    But the updated System76 Adder Pro also packs features like discrete graphics and an OLED display with a high refresh rate, which means that it’ll both be a better fit for gaming or mobile […]

    #amd #amdRyzenHalo #bigme #bigmeB251Pro #eInkMonitor #flipperZero #google #hmd #lilbits #linuxLaptop #nokia #pixel11 #pixel11Fold #pixel11Pro #ryzenHalo #steamMachine #strixHalo #system76AderPro #Valve Read more: liliputing.com/lilbits-flipper
  47. Lilbits: Flipper Zero’s firmware future, a new Linux gaming laptop, an E Ink monitor, and AMD’s pricey Ryzen Halo mini PC

    Shortly after launching a new thin and light Linux laptop with an Intel Panther Lake processor, Linux PC company System76 is preparing to launch… another notebook that could be described the same way.

    But the updated System76 Adder Pro also packs features like discrete graphics and an OLED display with a high refresh rate, which means that it’ll both be a better fit for gaming or mobile […]

    #amd #amdRyzenHalo #bigme #bigmeB251Pro #eInkMonitor #flipperZero #google #hmd #lilbits #linuxLaptop #nokia #pixel11 #pixel11Fold #pixel11Pro #ryzenHalo #steamMachine #strixHalo #system76AderPro #Valve Read more: liliputing.com/lilbits-flipper
  48. Lilbits: Flipper Zero’s firmware future, a new Linux gaming laptop, an E Ink monitor, and AMD’s pricey Ryzen Halo mini PC

    Shortly after launching a new thin and light Linux laptop with an Intel Panther Lake processor, Linux PC company System76 is preparing to launch… another notebook that could be described the same way.

    But the updated System76 Adder Pro also packs features like discrete graphics and an OLED display with a high refresh rate, which means that it’ll both be a better fit for gaming or mobile […]

    #amd #amdRyzenHalo #bigme #bigmeB251Pro #eInkMonitor #flipperZero #google #hmd #lilbits #linuxLaptop #nokia #pixel11 #pixel11Fold #pixel11Pro #ryzenHalo #steamMachine #strixHalo #system76AderPro #Valve Read more: liliputing.com/lilbits-flipper
  49. Lilbits: Flipper Zero’s firmware future, a new Linux gaming laptop, an E Ink monitor, and AMD’s pricey Ryzen Halo mini PC

    Shortly after launching a new thin and light Linux laptop with an Intel Panther Lake processor, Linux PC company System76 is preparing to launch… another notebook that could be described the same way.

    But the updated System76 Adder Pro also packs features like discrete graphics and an OLED display with a high refresh rate, which means that it’ll both be a better fit for gaming or mobile […]

    #amd #amdRyzenHalo #bigme #bigmeB251Pro #eInkMonitor #flipperZero #google #hmd #lilbits #linuxLaptop #nokia #pixel11 #pixel11Fold #pixel11Pro #ryzenHalo #steamMachine #strixHalo #system76AderPro #Valve Read more: liliputing.com/lilbits-flipper
  50. The AMD Ryzen Halo mini workstation with Ryzen AI MAX+ 395, 128GB LPDDR5x RAM, a 2TB SSD, 10 Gigabit Ethernet, and Windows and Linux support is now available from Micro Center... for $4000. amd.com/en/blogs/2026/amd-ryze #RyzenHalo #MiniPC #StrixHalo #AMD

  51. The AMD Ryzen Halo mini workstation with Ryzen AI MAX+ 395, 128GB LPDDR5x RAM, a 2TB SSD, 10 Gigabit Ethernet, and Windows and Linux support is now available from Micro Center... for $4000. amd.com/en/blogs/2026/amd-ryze

  52. The AMD Ryzen Halo mini workstation with Ryzen AI MAX+ 395, 128GB LPDDR5x RAM, a 2TB SSD, 10 Gigabit Ethernet, and Windows and Linux support is now available from Micro Center... for $4000. amd.com/en/blogs/2026/amd-ryze #RyzenHalo #MiniPC #StrixHalo #AMD