localai.computer

Loading content...

GPUs for AI Models: Benchmarks & Specs

Can AMD Instinct MI300X run Qwen/Qwen2.5-Coder-1.5B?

Runs Q4192GB VRAM availableRequires 3GB+

AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of Qwen/Qwen2.5-Coder-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	192GB	737.09 tok/s	✅ Fits comfortably
Q8	5GB	192GB	570.76 tok/s	✅ Fits comfortably
FP16	11GB	192GB	304.96 tok/s	✅ Fits comfortably

Suitable alternatives

NVIDIA H200 SXM 141GB

141GB

749.08 tok/s

Price: —

NVIDIA H100 SXM5 80GB

80GB

540.37 tok/s

Price: —

AMD Instinct MI250X

128GB

More questions

AMD Instinct MI300X specs & pricing Full guide for Qwen/Qwen2.5-Coder-1.5B