RTX 5090~154 tok/s (Q4)

lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-8bit speed on RTX 5090

Quantization-specific throughput and VRAM requirements for lmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-8bit running on RTX 5090.

Speed Snapshot

Topline estimate from compatibility data

Modellmstudio-community/Qwen3-Coder-30B-A3B-Instruct-MLX-8bit

GPURTX 5090

Q4 speed154 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	32GB	154 tok/s	✅ Fits
Q8	31GB	32GB	121 tok/s	⚠️ Tight fit
FP16	61GB	32GB	62 tok/s	❌ Not recommended