AMD Instinct MI250X~52 tok/s (Q4)

stepfun-ai/Step-3.5-Flash speed on AMD Instinct MI250X

Quantization-specific throughput and VRAM requirements for stepfun-ai/Step-3.5-Flash running on AMD Instinct MI250X.

Speed Snapshot

Topline estimate from compatibility data

Modelstepfun-ai/Step-3.5-Flash

GPUAMD Instinct MI250X

Q4 speed52 tok/s

Q4 VRAM required112GB

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	112GB	128GB	52 tok/s	✅ Fits
Q8	223GB	128GB	42 tok/s	❌ Not recommended
FP16	446GB	128GB	21 tok/s	❌ Not recommended