localai.computer

Loading content...

GPUs for AI Models: Benchmarks & Specs

Can AMD Instinct MI300X run deepseek-ai/deepseek-coder-1.3b-instruct?

Runs Q4192GB VRAM availableRequires 2GB+

AMD Instinct MI300X meets the minimum VRAM requirement for Q4 inference of deepseek-ai/deepseek-coder-1.3b-instruct. 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	2GB	192GB	921.11 tok/s	✅ Fits comfortably
Q8	3GB	192GB	656.94 tok/s	✅ Fits comfortably
FP16	6GB	192GB	379.91 tok/s	✅ Fits comfortably

Suitable alternatives

NVIDIA H200 SXM 141GB

141GB

759.45 tok/s

Price: —

AMD Instinct MI250X

128GB

578.16 tok/s

Price: —

NVIDIA H100 SXM5 80GB

80GB

More questions

AMD Instinct MI300X specs & pricing Full guide for deepseek-ai/deepseek-coder-1.3b-instruct