localai.computer

Loading content...

GPUs for AI Models: Benchmarks & Specs

Can NVIDIA H200 SXM 141GB run deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B?

Runs Q4141GB VRAM availableRequires 3GB+

NVIDIA H200 SXM 141GB meets the minimum VRAM requirement for Q4 inference of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B. Review the quantization breakdown below to see how higher precision settings impact VRAM and throughput.

Quantization breakdown

Quantization	VRAM needed	VRAM available	Estimated speed	Verdict
Q4	3GB	141GB	680.96 tok/s	✅ Fits comfortably
Q8	5GB	141GB	440.85 tok/s	✅ Fits comfortably
FP16	11GB	141GB	258.50 tok/s	✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X

192GB

811.69 tok/s

Price: —

AMD Instinct MI300X

192GB

577.47 tok/s

Price: —

AMD Instinct MI250X

128GB

More questions

NVIDIA H200 SXM 141GB specs & pricing Full guide for deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B