AMD Instinct MI300X~400 tok/s (Q4)

lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-6bit speed on AMD Instinct MI300X

Quantization-specific throughput and VRAM requirements for lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-6bit running on AMD Instinct MI300X.

Speed Snapshot

Topline estimate from compatibility data

Modellmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-6bit

GPUAMD Instinct MI300X

Q4 speed400 tok/s

Q4 VRAM required15GB

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	15GB	192GB	400 tok/s	✅ Fits
Q8	31GB	192GB	278 tok/s	✅ Fits
FP16	61GB	192GB	161 tok/s	✅ Fits