#vram — Public Fediverse posts

السّلام عليكم
ليوم في
#Linux, #Privacy, Open-source and open-web #news
Linux 7.3
حسب الأخبار الحاليّة ينجّم يحسّن إستعمالو على الماكينات "البطاطا"
"Potato" #PCs
بالتّحديد في مجال ال
#Gaming
بتحسين التّعامل مع ال
#VRAM
الشّويّة
https://pixelcluster.dev/VRAM-Overcommit/
الوحيد إلّي يحبّوا يجرّبوا
#Linux
ماغير ما يعملوا المرج متاع صبّانو، ثمّة حاجة إسمها
#WSL (Windows Subsystem for Linux)
إلّي يخلّيك تجرّب برشة
#Distributions
على
windows
منهم
#Ubuntu
إلّي تشهد نموّ أكثر من إستعمالو بالطّريقة التّقليديّة
https://www.windowslatest.com/2026/08/16/ubuntu-is-growing-faster-on-windows-11-than-on-native-linux-pcs-says-canonical/

https://blog.gslin.org/archives/2026/08/20/13160/unsloth-%e7%9a%84-ud-3-0/

Unsloth 的 UD 3.0

#ai #dynamic #language #large #llm #memory #model #quantization #ram #video #vram

hw-smi v1.6 brings support for data logging!

You have requested an option to log the telemetry data (#GPU​/VRAM usage, #VRAM bandwidth, temperature, power, fan speed, #PCIe bandwidth etc.) from hw-smi to a file. Today I have implemented exactly that. Have fun montoring your hardware and applications, be it #Intel Arc (Pro) or any other #Nvidia​/​#AMD GPUs on Windows and #Linux! 🖖

https://github.com/ProjectPhysX/hw-smi/releases/tag/v1.6

🎉 #Linux 7.3: Now celebrating the revolutionary concept of "Don't run out of #VRAM, or else!" 🙃 Apparently, the pinnacle of #innovation is making sure you don't overpromise your virtual memory—truly groundbreaking stuff for the #gaming elite. 🚀
https://pixelcluster.dev/VRAM-Overcommit/ #7.3 #LinuxNews #HackerNews #ngated

Linux 7.3 improves performance when running out of vRAM

https://pixelcluster.dev/VRAM-Overcommit/

Comments: https://news.ycombinator.com/item?id=49342719

#HackerNews #Linux #vRAM #Performance #Improvement #Performance #Tuning #Tech #News #Open #Source

NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
Today the market difference is $191.
The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

https://www.buysellram.com/blog/nvidia-consumer-gpu-price-report-august-2026/

#NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #technology

NVIDIA sold the RTX 5060 Ti with 8GB or 16GB. Same chip. Launch price difference: $50.
Today the market difference is $191.
The 4060 Ti ran the same experiment two years earlier and landed within 50 cents per gigabyte.

https://www.buysellram.com/blog/nvidia-consumer-gpu-price-report-august-2026/

#NVIDIA #GPUPrices #RTX50 #RTX5090 #VRAM #GDDR7 #DRAM #GPU #PCHardware #ITAD #ITAssetDisposition #DataCenter #ResaleValue #tech

NVIDIA RTX PRO 5000 Blackwell с 72 Гб видеопамяти. Есть ли смысл переплачивать за «половинку» флагмана?

RTX PRO 5000 Blackwell на 72 Гб: золотая середина для локальных ИИ-моделей или переоцененный апгрейд? Разбираемся в нашем обзоре.

https://habr.com/ru/companies/hostkey/articles/1067786/

#NVIDIA #Blackwell #RTX_PRO_5000 #GPU #VRAM #LLM #инференс #DeepSeek #CUDA #hostkey

https://blog.gslin.org/archives/2026/08/01/13133/%e8%b2%b7%e4%ba%86%e5%bc%b5-intel-arc-pro-b70-32gb-vram-%e4%be%86%e7%8e%a9/

買了張 Intel Arc Pro B70 (32GB VRAM) 來玩...

#36 #32gb #above #ai #arc #b70 #bar #bios #csm #debian #decoding #express #firmware #gguf #intel #kernel #language #large #linux #LlamaCpp #llm #model #pci #PciE #pro #qwen #resize #setup #support #sycl #vram #vulkan

💻🎮 Ah, the RTX 2080 Ti memory upgrade! Because who doesn't want to spend more on an ancient card instead of just buying a new one? 🙄 Double the #VRAM, double the opportunity to brag about your retro tech expertise at your next LAN party. 😂
https://gpusolutions.net/rbservices/graphics-card-upgrade/ #RTX2080Ti #MemoryUpgrade #RetroTech #LANParty #GamingHumor #HackerNews #ngated

Industrial GPU Adapted for the Desktop

https://fed.brid.gy/r/https://hackaday.com/2026/07/22/industrial-gpu-adapted-for-the-desktop/

Tip I keep giving people about #ComputerHardware that I wonder if anyone has a counterpoint too...

A #GraphicsCard is still a Graphics Card, even if it's old or low end. Even the obsolete #NVIDIA 1050 in my laptop can render billions of polygons at 60fps, more if I give it external cooling, and is capable of every major shader operation, short of #Raytracing, that a newer card is: other than a potentially heavy short-term load like #Resonite and #Blender can throw when you're building something complicated, the only useful thing my cards are short on is #VRAM. Hell, even the embedded #GPU in the old i7 #CPU, and the #iGPU in my desktop's #AMD 7600 can run less intensive games like Black Mesa without many issues. (I know this because I've run them with the graphics card deactivated, I actually can't get Black Mesa to run with it.)

If you're building a computer and don't know what to get, just get the cheapest graphics card that meets your VRAM needs. (Probably at least 8GB with how unoptimized User Generated Content in spaces like Resonite can get, or how unoptimized "professional" developers have gotten)

Outside of specific issues, there's really not much need to get the high tier or later cards, unless you know a specific need for it: the 5 year old mid-tier will give you a passable experience in the majority of cases, and will likely have fewer driver/compatibility issues anyway. Newer and higher tier is just not worth another few hundred dollars these days.

Someone else may have a reason I'm wrong though: I'm open to a reason this is bad advice.

Почему дорогая LLM дороже: экономика инференса, которую видно в твоём 5-часовом лимите

Каждый из вас, кто работал с Claude или с ChatGPT, смотрел на свои лимиты Или задавался вопросом «Да как один запрос съел 10% от лимита» Я потратил неделю на то, чтобы разобраться в том, а что вообще отображают эти лимиты И на свет появилась третья статья из моей серии «А как вообще работают современные LLM» После этой статьи ты разберёшься, что скрыто за 5-часовым лимитом Claude и других LLM и как на этом можно экономить. А еще — из каких примитивов состоят лимиты и какая физика вычислений за этим стоит Ну а если работаешь с моделями по API, то вообще пушка бомба Осторожно: после прочтения вы не сможете смотреть на полоску лимитов как прежде 🥵 Че там Че там 👀

https://habr.com/ru/articles/1055054/

#LLM #MoE #activeпараметры #KVcache #инференс_LLM #outputтокены #reasoningтокены #VRAM #claude_code #codex

«Бери новое поколение» и другие плохие советы по выбору GPU в 2026 году

Привет, Хабр! На связи Илья Мартысь из Рег.облака. Каждый раз, когда выходит новое поколение ускорителей, в чатах начинается одно и то же: «брать B300 или хватит H200?». И отвечают на это табличкой со спеками — вот память, вот терафлопсы, новое лучше. Тут есть нюанс. В момент выхода нового поколения вопрос «брать ли его» обычно даже не стоит: оно появляется на рынке с задержкой в год-два. Реальный вопрос другой — когда начинать переплачивать за новое и нужно ли оно вашему проекту вообще. Дальше разберем это по двум вещам, которые в

https://habr.com/ru/companies/runity/articles/1050738/

#регоблако #gpu #графика #жесткий_диск #hopper_gpu #hopper #blackwell #vram #память #память_ии

Ein Modder hat die Leistung seiner #Nvidia #GeForce #GTX1650 verdoppelt, indem er mehr #VRAM auf die Platine lötete. https://winfuture.de/news,159492.html?utm_source=Mastodon&utm_medium=ManualStatus&utm_campaign=SocialMedia

The #OpenCode is working. Check when the Nvidia is used for it
⎿  [Image #1]

● I'll check how #Ollama uses the #Nvidia GPU.

● Bash(nvidia-smi --query-gpu=name,memory.used,memory.total,utilization.gpu --format=csv,noheader 2>/dev/null)
⎿  NVIDIA GeForce RTX 2060, 952 MiB, 6144 MiB, 9 %

● Bash(ollama ps 2>/dev/null)
⎿  NAME ID SIZE PROCESSOR UNTIL
qwen2.5-coder:7b-16k 0533dd01f237 7.2 GB 30%/70% CPU/GPU 4 minutes from now

● The model is currently loaded and actively using the GPU. Here's the breakdown:

- Model: #qwen2.5-coder:7b-16k — 7.2 GB total
- Split: 30% CPU / 70% GPU — the model is split across RAM and VRAM because it doesn't fit entirely in the RTX 2060's 6 GB VRAM
- Current #GPU #VRAM usage: 952 MiB used of 6144 MiB (the rest of the model layers sit in system RAM)
- GPU compute utilization: 9% right now (idle between requests)

The GPU is used whenever OpenCode sends a prompt to Ollama — during inference, 70% of the model layers run on the #RTX2060 and 30% on the #CPU. The model stays loaded in VRAM for 4 more minutes of idle time before Ollama unloads it.

#LocalLLM

@jwildeboer i think it should be possible to combine CPU+RAM and GPU+VRAM but most models just say #nah if there is not enough expensive #VRAM question: what about distributed computing?
#gpt4all https://dwaves.de/2023/12/16/gnu-linux-how-to-install-gpt4all-on-debian-12-gpt4all-j-an-apache-2-licensed-assistant-style-chatbot-a-free-to-use-locally-running-privacy-aware-chatbot-no-gpu-or-internet-required-dialogu/
#deepseek can run on #cpu but its slow https://dwaves.de/2025/02/01/also-with-ai-opensource-for-the-win-cpu-only-benchmarking-deepseek-on-local-amd-server-can-it-be-funny/

VRAM Dominance: The Unseen King in Local LLM Operations

Local LLM operators find VRAM capacity more important than speed for running models. Learn what VRAM size you need for different LLM sizes.

#LLM, #VRAM, #GPU, #AI, #Tech

https://newsletter.tf/vram-capacity-for-local-llm-operations/

Running large language models locally needs more VRAM than processing power. A card with 24GB VRAM can run bigger models better than a faster card with less memory.

#LLM, #VRAM, #GPU, #AI, #Tech
https://newsletter.tf/vram-capacity-for-local-llm-operations/