Run MiMo-V2.6-Flash on M3 Ultra

Yes — MiMo-V2.6-Flash (309B-A15B) runs at 30 tok/s on M3 Ultra with 256 GB RAM using MXFP4 quantization via MLX. A capable open-source LLM with 309B-A15B parameters.

Speed

estimated30

tok/s

First Token

—

seconds

RAM Needed

256

GB minimum

Engine

MLX

Benchmark Details

The LLMCheck index estimates MiMo-V2.6-Flash on M3 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 →

Metric	Value
Tokens per second	30 tok/s
Time to first token	—
Quantization	MXFP4
Minimum RAM	256 GB
Recommended engine	MLX
Parameters	309B-A15B
Benchmark date	2026-09

MXFP4 309B-A15B MLX M3 Ultra

Setup Guide: Run MiMo-V2.6-Flash on M3 Ultra

The recommended engine for MiMo-V2.6-Flash on M3 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/mimo-v26-flash-mxfp4 --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run mimo-v26-flash

System Requirements

To run MiMo-V2.6-Flash on M3 Ultra you need:

• Mac with M3 Ultra chip (or newer)
• 256 GB unified memory minimum
• macOS 13 Ventura or later
• ~217-256 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

🛒 Get a Mac that runs MiMo-V2.6-Flash

MiMo-V2.6-Flash needs about 256 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

Mac Studio M5 Ultra (512GB) on Amazon → Mac Studio M4 Ultra (192GB) on Amazon →

As an Amazon Associate, LLMCheck earns from qualifying purchases. These affiliate links cost you nothing extra and help keep the LLMCheck index free.

Compare More Models

See how MiMo-V2.6-Flash stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard