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

tok/s

First Token

0.5

seconds

RAM Needed

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured Ministral 8B on M4 using the standard methodology: Q4_K_M quantization, 256-token input, 512-token output, 3 runs averaged on a freshly-booted system.

Metric	Value
Tokens per second	72 tok/s
Time to first token	0.5s
Quantization	Q4_K_M
Minimum RAM	16 GB
Recommended engine	MLX
Parameters	8B
Benchmark date	2026-02

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

Chip	Speed	First Token	Min RAM	Engine
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:

• Mac with M4 chip (or newer)
• 16 GB unified memory minimum
• macOS 13 Ventura or later
• ~13-16 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

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

Open Compare Tool Full Leaderboard