Run Mistral Small 4 on M5 Max

Yes — Mistral Small 4 (119B) runs at 38 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.9s. Mistral's 119B MoE model with enterprise-grade quality — requires 128 GB Mac.

Speed
38
tok/s
First Token
0.9
seconds
RAM Needed
128
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Mistral Small 4 on M5 Max 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 second38 tok/s
Time to first token0.9s
QuantizationQ4_K_M
Minimum RAM128 GB
Recommended engineOllama
Parameters119B
Benchmark date2026-04

Q4_K_M 119B Ollama M5 Max

Setup Guide: Run Mistral Small 4 on M5 Max

The recommended engine for Mistral Small 4 on M5 Max is Ollama. Install Ollama, then pull the model:

ollama run mistral-small:4

Ollama handles quantization automatically — it will download the Q4_K_M variant (~128 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 Ultra 45 tok/s 0.7s 192 GB MLX

System Requirements

To run Mistral Small 4 on M5 Max you need:

Compare More Models

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

Open Compare Tool Full Leaderboard