Run Mistral Voyage Pro 70B on M5 Max

Yes — Mistral Voyage Pro 70B (70B) runs at 16 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via MLX. First token latency is 1.8s. A capable open-source LLM with 70B parameters.

Speed
16
tok/s
First Token
1.8
seconds
RAM Needed
128
GB minimum
Engine
MLX
recommended
Want to run Mistral Voyage Pro 70B faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Mistral Voyage Pro 70B on M5 Max 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 second16 tok/s
Time to first token1.8s
QuantizationQ4_K_M
Minimum RAM128 GB
Recommended engineMLX
Parameters70B
Benchmark date2026-06

Q4_K_M 70B MLX M5 Max

Setup Guide: Run Mistral Voyage Pro 70B on M5 Max

The recommended engine for Mistral Voyage Pro 70B on M5 Max is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/mistral-voyage-pro-70b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run mistral-voyage-pro-70b

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M4 Ultra 20 tok/s 1.5s 192 GB Ollama
M4 Max 13 tok/s 2.1s 128 GB MLX

System Requirements

To run Mistral Voyage Pro 70B on M5 Max you need:

🛒 Get a Mac that runs Mistral Voyage Pro 70B

Mistral Voyage Pro 70B needs about 128 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 Mistral Voyage Pro 70B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard