Run Ministral 8B on M3

Yes — Ministral 8B (8B) runs at 55 tok/s on M3 with 16 GB RAM using Q4_K_M quantization via LM Studio. First token latency is 0.7s. Mistral's 8B model optimized for edge inference with strong instruction following.

Speed
55
tok/s
First Token
0.7
seconds
RAM Needed
16
GB minimum
Engine
LM Studio
recommended

Benchmark Details

LLMCheck measured Ministral 8B on M3 using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

MetricValue
Tokens per second55 tok/s
Time to first token0.7s
QuantizationQ4_K_M
Minimum RAM16 GB
Recommended engineLM Studio
Parameters8B
Benchmark date2026-01

Q4_K_M 8B LM Studio M3

Setup Guide: Run Ministral 8B on M3

The recommended engine for Ministral 8B on M3 is LM Studio. Install Ollama, then pull the model:

ollama run ministral:8b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~16 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 98 tok/s 0.4s 64 GB Ollama
M4 72 tok/s 0.5s 16 GB MLX

System Requirements

To run Ministral 8B on M3 you need:

Compare More Models

See how Ministral 8B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard