Run Ministral 8B on M4

Yes — Ministral 8B (8B) runs at 72 tok/s on M4 with 16 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.5s. Mistral's 8B model optimized for edge inference with strong instruction following.

Speed
72
tok/s
First Token
0.5
seconds
RAM Needed
16
GB minimum
Engine
MLX
recommended
Want to run Ministral 8B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Ministral 8B on M4 using our published methodology: Q4_K_M quantization, memory-bandwidth scaling, and cross-referenced third-party benchmarks where available. Figures are transparent estimates — own this config? Submit a real benchmark →

MetricValue
Tokens per second72 tok/s
Time to first token0.5s
QuantizationQ4_K_M
Minimum RAM16 GB
Recommended engineMLX
Parameters8B
Benchmark date2026-02

Q4_K_M 8B MLX M4

Setup Guide: Run Ministral 8B on M4

The recommended engine for Ministral 8B on M4 is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/ministral-8b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run ministral:8b

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 98 tok/s 0.4s 64 GB Ollama
M3 55 tok/s 0.7s 16 GB LM Studio

System Requirements

To run Ministral 8B on M4 you need:

🛒 Get a Mac that runs Ministral 8B

Ministral 8B needs about 16 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep our benchmarks free.

Compare More Models

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

Open Compare Tool Full Leaderboard