Run Mistral Small 4 on M4 Ultra

Yes — Mistral Small 4 (119B) runs at 45 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.7s. Mistral's 119B MoE model with enterprise-grade quality — requires 128 GB Mac.

Speed

tok/s

First Token

0.7

seconds

RAM Needed

192

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured Mistral Small 4 on M4 Ultra 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	45 tok/s
Time to first token	0.7s
Quantization	Q4_K_M
Minimum RAM	192 GB
Recommended engine	MLX
Parameters	119B
Benchmark date	2026-04

Q4_K_M 119B MLX M4 Ultra

Setup Guide: Run Mistral Small 4 on M4 Ultra

The recommended engine for Mistral Small 4 on M4 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/mistral-small-4-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run mistral-small:4

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M5 Max	42 tok/s	0.8s	128 GB	MLX
M5 Max	38 tok/s	0.9s	128 GB	Ollama

System Requirements

To run Mistral Small 4 on M4 Ultra you need:

• Mac with M4 Ultra chip (or newer)
• 192 GB unified memory minimum
• macOS 13 Ventura or later
• ~163-192 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

See how Mistral Small 4 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard