AMD Instinct MI250X~97 tok/s (Q4)

Qwen/Qwen3-Coder-Next speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for Qwen/Qwen3-Coder-Next running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

ModelQwen/Qwen3-Coder-Next

GPUAMD Instinct MI250X

Q4 speed97 tok/s

Q4 VRAM required45GB

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	45GB	128GB	97 tok/s	✅ Fits
Q8	90GB	128GB	67 tok/s	✅ Fits
FP16	179GB	128GB	33 tok/s	❌ Not recommended