NVIDIA L40~119 tok/s (Q4)

mistralai/Ministral-3-14B-Instruct-2512 speed on NVIDIA L40

Quantization-specific throughput and VRAM requirements for mistralai/Ministral-3-14B-Instruct-2512 running on NVIDIA L40.

Speed Snapshot

Topline estimate from compatibility data

Modelmistralai/Ministral-3-14B-Instruct-2512

GPUNVIDIA L40

Q4 speed119 tok/s

Q4 VRAM required8GB

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	8GB	48GB	119 tok/s	✅ Fits
Q8	16GB	48GB	87 tok/s	✅ Fits
FP16	32GB	48GB	46 tok/s	✅ Fits