localai.computer

Loading content...

GPUs for AI Models: Benchmarks & Specs

Can NVIDIA H200 SXM 141GB run codellama/CodeLlama-34b-hf?

Runs Q4141GB VRAM availableRequires 17GB+

NVIDIA H200 SXM 141GB meets the minimum VRAM requirement for Q4 inference of codellama/CodeLlama-34b-hf. 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	17GB	141GB	217.90 tok/s	✅ Fits comfortably
Q8	35GB	141GB	152.19 tok/s	✅ Fits comfortably
FP16	70GB	141GB	85.74 tok/s	✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X

192GB

278.02 tok/s

Price: —

AMD Instinct MI300X

192GB

190.11 tok/s

Price: —

AMD Instinct MI250X

128GB

More questions

NVIDIA H200 SXM 141GB specs & pricing Full guide for codellama/CodeLlama-34b-hf