Search results

I failed on this

The Nvidia A100 32G SXM2 PG199+FA2 can support local agentic coding tools like Roo, Cline, and Kilo, with acceptable output speeds. Taking Qwen3 Coder 30b as an example, chat performance reaches 80-90 TPS, but drops to 40-50 TPS when using agent due to the long context window. With contexts...

Congratulations, this is incredibly delicate, I can't do this. It's like a surgical operation.

Can I ask why you want to disassemble this SXM2? My current application is mainly LLM inference. Using the latest MOE architecture such as Qwen3 or GLM, the heat problem has been greatly reduced. I used to use three three-fan air cooling, each fan power is 6Watt, but now, three fans only use...

I am sharing a very good blog about a PG199 experience (I really admire the author’s perseverance and research spirit), but if you don’t like it please just ignore it. Making a datacenter gpu server in my student bedroom

got it and show me something useful as an example, pls

https://hothardware.com/news/nvidia-drive-agx-pegasus-orin-ampere-next-gen-autonomous-cars

NVIDIA DRIVE A100 Automotive SXM2 GPU (Model: 900-6G199-0000-C00) for Autonomous Vehicles Specifications Key Features: Model Number: 900-6G199-0000-C00 Product Type: Automotive GPU Architecture: NVIDIA Ampere Form Factor: SXM2 (for integration into automotive systems) Target Application...

i installed 2pcs into my ATX boxed PC and 2pcs as eGPU for my laptop (usually i only use 1pcs)

maybe yes, upon your use case, but i am happy with them together with exllamav2 for Qwen series inference, super fast :D

I just haven't paid attention for a few months, and almost all the low-priced PG199s on eBay are sold out. Maybe more people are discovering the trick of using this computing card.

Thanks for sharing the insights.

I don't know if it's really necessary to do that. With three fans and five heat pipes on an open rack, the temperature of the PG199 inference model can be controlled below 70 degrees. Will this affect the secondary sale?