#strixhalo — Public Fediverse posts

I think this may be my main daily driver for the foreseeable future on my #StrixHalo. (Provided no major model drops but this one seems to have everything I want. Always been a fan of Ciru's work and his green haired AI genned waifu

https://huggingface.co/jcbtc/Qwen3.8-Flash-CIRU-STRIX-Orca

@grymas1000lecia proszę bardzo: https://www.bosgame.com/products/bosgame-m5-ai-mini-desktop-ryzen-ai-max-395-96gb-128gb-2tb?variant=46726110707875 najtańszy komp w tej konfiguracji procesor+GPU #LLM #strixhalo

@grymas1000lecia proszę bardzo: https://www.bosgame.com/products/bosgame-m5-ai-mini-desktop-ryzen-ai-max-395-96gb-128gb-2tb?variant=46726110707875 najtańszy komp w tej konfiguracji procesor+GPU #LLM #strixhalo

@grymas1000lecia proszę bardzo: https://www.bosgame.com/products/bosgame-m5-ai-mini-desktop-ryzen-ai-max-395-96gb-128gb-2tb?variant=46726110707875 najtańszy komp w tej konfiguracji procesor+GPU #LLM #strixhalo

@grymas1000lecia proszę bardzo: https://www.bosgame.com/products/bosgame-m5-ai-mini-desktop-ryzen-ai-max-395-96gb-128gb-2tb?variant=46726110707875 najtańszy komp w tej konfiguracji procesor+GPU #LLM #strixhalo

Nutze ja seit Monaten #hermesagent - eben zum ersten Mal /yolo verwendet - Game Changer bei laaaaaangsamen llms wie #qwen38 auf meinem #strixhalo

#appliedai

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

Great DGX upsell, btw.

https://videocardz.com/newz/amd-launches-3999-ryzen-ai-halo-pc-limited-to-one-us-retailer

#AMD #Ryzen #RyzenAI #StrixHalo #Zen5 #RDNA3 #AI #LLM #ArtificialIntelligence

A mini PC the size of a paperback can now run a 200B-parameter model locally. But choosing one isn't about the lowest price tag. Capacity sets what fits, bandwidth sets how fast it runs, and the software stack — CUDA, ROCm, or Metal — decides whether your tools work at all. Here's how the four real options compare in 2026, with current prices and benchmarks.
https://www.buysellram.com/blog/how-to-choose-the-best-mini-pc-for-local-ai-in-2026/
#LocalAI #LLM #MiniPC #AIhardware #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #RyzenAI #AIPC #AMD #NVIDIA #Apple

Choosing A mini PC isn't about the lowest price tag. Capacity sets what fits, bandwidth sets how fast it runs, and the software stack — CUDA, ROCm, or Metal — decides whether your tools work at all. Here's how the four real options compare in 2026, with current prices and benchmarks.
https://www.buysellram.com/blog/how-to-choose-the-best-mini-pc-for-local-ai-in-2026/
#LocalAI #LLM #MiniPC #AIhardware #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #AIinfrastructure #Ollama #RyzenAI #AIPC #AMD #NVIDIA

AMD Ryzen AI Max+ 395 vs Nvidia DGX Spark vs Apple Mac — plus when a GPU tower still beats all three. A practical hardware guide for IT managers, developers, and small-business owners weighing a local LLM machine.

Running large language models locally went from a niche hobby to a real procurement question in 2026. A mini PC the size of a paperback can now hold a 200-billion-parameter model — the kind of workload that used to need a server rack.

But picking one isn't about the lowest price. Three things decide whether a model runs well: memory capacity (what fits), memory bandwidth (how fast it runs), and the software ecosystem — CUDA, ROCm, or Metal — that determines whether your existing tools work at all.

There are four real ways to run a local LLM on your desk: a discrete-GPU tower (fastest, but a VRAM wall), AMD Strix Halo mini PCs (big unified memory, cheap, Windows-native), Nvidia's GB10 boxes like the DGX Spark and Dell Pro Max (CUDA, but now $4,699 and Linux-only), and Apple's Mac mini and Mac Studio (high bandwidth, silent, no CUDA).

This guide breaks down which fits which job — with verified specs and current prices.

An appendix at the end collects what early buyers of the AMD “lunchbox” are actually reporting.

https://www.buysellram.com/blog/how-to-choose-the-best-mini-pc-for-local-ai-in-2026/
#LocalAI #LLM #MiniPC #AIhardware #StrixHalo #DGXSpark #AppleSilicon #EdgeAI #AIinfrastructure #Ollama #RyzenAI #AIPC #AMD #NVIDIA #Apple #technology

A mini PC the size of a paperback can now run a 200B-parameter model locally. But choosing one isn't about the lowest price tag. Capacity sets what fits, bandwidth sets how fast it runs, and the software stack — CUDA, ROCm, or Metal — decides whether your tools work at all. Here's how the four real options compare in 2026, with current prices and benchmarks.
https://www.buysellram.com/blog/how-to-choose-the-best-mini-pc-for-local-ai-in-2026/
#LocalAI #LLM #MiniPC #AIhardware #StrixHalo #DGXSpark #EdgeAI #AIinfrastructure #tech #RyzenAI #NVIDIA #Apple

More Ryzen AI Max+ 395 mini PCs with 128GB are now available… if you can afford one

AMD’s Ryzen AI Max+ 395 Strix Halo processor packs a lot of power into a mobile chip designed for laptops and mini PCs. With integrated graphics that rivals a discrete GPU, it offers an efficient solution for gaming, graphics, or AI workloads. And with support for up to 128GB of high-speed, high-bandwidth memory, most of which can be used as VRAM, most PCs using the chip are marketed as AI […]

Neue CPUs von AMD: Ryzen 9700X3D und AI Max+ 388/392 gesichtet (Update) https://www.computerbase.de/news/prozessoren/neue-cpus-von-amd-ryzen-9700x3d-und-ai-max-plus-388-392-gesichtet.94924/#update-2025-11-08T18:41 #ryzen #9700X3D #strixhalo

AMD Strix Halo lineup expands with cheaper chips sporting Radeon 40-core Radeon 8060S graphics

The AMD Strix Halo line of processors are mobile chips that combine high-performance Zen 5 CPU cores with enough RDNA 3.5 GPU compute units to offer integrated graphics with discrete-class performance. When combined with high-bandwidth onboard memory, this makes these chips ideal for compact AI workstations, but they’ve also shown up in a few gaming tablets and handhelds.

Now it looks like AMD […]

#amd #chips #radeon8060s #ryzenAiMax #ryzenAiMax300 #strixHalo

Read more: https://liliputing.com/amd-strix-halo-lineup-expands-with-cheaper-chips-sporting-radeon-40-core-radeon-8060s-graphics/

Neue CPUs von AMD: Ryzen 9700X3D und AI Max+ 388/392 gesichtet https://www.computerbase.de/news/prozessoren/neue-cpus-von-amd-ryzen-9700x3d-und-ai-max-plus-388-392-gesichtet.94924/ #ryzen #9700X3D #strixhalo

Lilbits: Atari and Intellivision made a retro console (kind of), Google’s Privacy Sandbox is gone for good, and Amazon’s Fire TV Stick 4K Select with Vega OS is a lot more locked down

Atari and Intellivision have a few things in common. They were two of the first big players in the home video game console space. And neither brand is what it once was anymore.

So while it’s intriguing to see that Atari is launching a new retro console called the Intellivision Sprint, this is really a partnership between the company that now owns the rights to the Atari name and retro game […]

#amazonFireTvStick4kSelect #atari #bluetoothSpeaker #edifier #fairphone #fairphone4 #fireTvStick4kSelect #google #intellivision #intellivisionSprint #lilbits #linuxLaptop #morefineH1 #ploopy #privacySandbox #retroConsole #retroGaming #samsungGalaxyS26Edge #strixHalo #tuxedoInfinitybookPro15 #vegaOs

Read more: https://liliputing.com/lilbits-atari-and-intellivision-made-a-retro-console-kind-of-googles-privacy-sandbox-is-gone-for-good-and-amazons-fire-tv-stick-4k-select-with-vega-os-is-a-lot-more-locked-down/

Bosgame M5 AI is a mini PC with Ryzen AI Max+ 395 (and a familiar design)

The Bosgame M5 AI is a small desktop computer with a powerful AMD Ryzen AI Max+ 395 Strix Halo processor featuring a 16-core, 32-thread CPU, Radeon 8060S integrated graphics with 40 RDNA 3.5 GPU cores, and an NPU that delivers up to 40 TOPS of AI performance.

Available for pre-order from the Bosgame website for $1699, it’s the latest in a run of powerful-but-expensive mini PCs with AMD Strix […]

#bosgame #bosgameM5Ai #miniPc #strixHalo

Read more: https://liliputing.com/bosgame-m5-ai-is-a-mini-pc-with-ryzen-ai-max-395-and-a-familiar-design/

AMD Strix Halo is coming to more mini PCs (eventually)

AMD’s Ryzen AI Max “Strix Halo” processors are high-performance mobile chips with integrated graphics that can rival recent mid-range discrete GPUs, support for up to 16 Zen 5 CPU cores, and an NPU that offers up to 50 TOPS of hardware-accelerated AI performance.

So far only a couple of companies have announced PCs that will actually use the chips though. There’s the Asus ROG Flow Z13 […]

#amd #gmk #miniPc #ryzenAiMax #strixHalo

Read more: https://liliputing.com/amd-strix-halo-is-coming-to-more-mini-pcs-eventually/

Asus ROG Flow Z13 Strix Halo gaming tablet is available for pre-order for $2100 and up

The new Asus ROG Flow Z13 is a Windows tablet with a 13.4 inch, 2560 x 1600 pixel, 180 Hz IPS LCD touchscreen display, a detachable keyboard and a ridiculously powerful processor.

Designed as a portable gaming computer that doesn’t need a discrete GPU, the tablet is powered by an AMD Ryzen AI Max processor with discrete-level integrated graphics. Asus unveiled the ROG Flow Z13 (2025) during […]

#amdRyzenAiMax #asus #asusRogFlowZ13 #gamingLaptop #gamingTablet #rogFlowZ13 #ryzenAiMax #strixHalo

Read more: https://liliputing.com/asus-rog-flow-z13-strix-point-gaming-tablet-is-available-for-pre-order-for-2100-and-up/

AMD has unveiled the Ryzen AI Max+ 395 processor, claiming to outperform Nvidia's RTX 4090 in AI efficiency and gaming benchmarks #AMD #StrixHalo #RyzenAIMax #CES2025 #AI #Gaming #NPU #AIComputing

https://winbuzzer.com/2025/01/06/amd-unveils-ryzen-ai-max-chips-for-mobile-ai-computing-xcxwbn/

AMD’s Ryzen AI Max “Strix Halo” are mobile chips with discrete-class graphics for gaming laptops and mobile workstations

The AMD Ryzen AI 300 Series “Strix Point” line of processors that debuted last summer pack a lot of performance into a mobile processor by combining up to 12 CPU cores based on Zen 5 architecture with up to 16 RDNA 3.5 GPU compute units.

AMD’s new Ryzen AI Max 300 Series “Strix Halo” go even further. These new chips feature up to 16 Zen 5 CPU cores and up to 40 GPU compute units. AMD says […]

#amd #ces2025 #chips #fireRange #ryzenAiMax #strixHalo

Read more: https://liliputing.com/amds-ryzen-ai-max-strix-halo-are-mobile-chips-with-discrete-class-graphics/

Given the pricing of #StrixPoint going from $1,200 upwards, I have ZERO faith on #StrixHalo sales.

Both Max 385 and Max 390 look like the sweet spots, but you won't beat the availability of #Intel laptops with #RTX cards starting at $800. And the #MacBook exists.

#AMD should really start to get their pricing right.

https://videocardz.com/newz/amd-strix-halo-igpu-naming-revealed-radeon-8060s-to-feature-40-rdna3-5-compute-units

#Laptop #NVIDIA #Zen5 #GeForce #GeForceRTX #PC #Computer #Computers #Hardware #PCHardware #Technology