localai.computer

Loading content...

GPUs for AI Models: Benchmarks & Specs

Can AMD Instinct MI250X run codellama/CodeLlama-34b-hf?

Runs Q4128GB VRAM availableRequires 17GB+

AMD Instinct MI250X 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	128GB	182.00 tok/s	✅ Fits comfortably
Q8	35GB	128GB	116.80 tok/s	✅ Fits comfortably
FP16	70GB	128GB	57.34 tok/s	✅ Fits comfortably

Suitable alternatives

AMD Instinct MI300X

192GB

278.02 tok/s

Price: —

NVIDIA H200 SXM 141GB

141GB

217.90 tok/s

Price: —

AMD Instinct MI300X

192GB

More questions

AMD Instinct MI250X specs & pricing Full guide for codellama/CodeLlama-34b-hf