Run MiniMax M2.5 on M4 Ultra

Yes — MiniMax M2.5 (230B-A10B) runs at 33 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.7s. A capable open-source LLM with 230B-A10B parameters.

Speed
33
tok/s
First Token
0.7
seconds
RAM Needed
192
GB minimum
Engine
MLX
recommended
Want to run MiniMax M2.5 faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates MiniMax M2.5 on M4 Ultra 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 second33 tok/s
Time to first token0.7s
QuantizationQ4_K_M
Minimum RAM192 GB
Recommended engineMLX
Parameters230B-A10B
Benchmark date2026-08

Q4_K_M 230B-A10B MLX M4 Ultra

Setup Guide: Run MiniMax M2.5 on M4 Ultra

The recommended engine for MiniMax M2.5 on M4 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/minimax-m25-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run minimax-m25

System Requirements

To run MiniMax M2.5 on M4 Ultra you need:

🛒 Get a Mac that runs MiniMax M2.5

MiniMax M2.5 needs about 192 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 MiniMax M2.5 stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard