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

AMD Instinct MI250X~86 tok/s (Q4)

Qwen/Qwen3-Next-80B-A3B-Thinking-FP8 speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for Qwen/Qwen3-Next-80B-A3B-Thinking-FP8 running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

ModelQwen/Qwen3-Next-80B-A3B-Thinking-FP8

GPUAMD Instinct MI250X

Q4 speed86 tok/s

Q4 VRAM required39GB

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	39GB	128GB	86 tok/s	✅ Fits
Q8	78GB	128GB	68 tok/s	✅ Fits
FP16	156GB	128GB	34 tok/s	❌ Not recommended