We earn from qualifying purchases through affiliate links at no extra cost to you. This supports our free content and research.

AMD Instinct MI300X~807 tok/s (Q4)

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modeldeepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

GPUAMD Instinct MI300X

Q4 speed807 tok/s

Q4 VRAM required3GB

Data Source

Calculation and benchmark status

Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.

For full verdict logic and alternate GPUs, see the canonical compatibility page.

Quantization Speed Table

Quantization	VRAM needed	VRAM available	Speed	Verdict
Q4	3GB	192GB	807 tok/s	✅ Fits
Q8	5GB	192GB	556 tok/s	✅ Fits
FP16	11GB	192GB	272 tok/s	✅ Fits