Run Llama 4 Scout on M5 Max

Yes — Llama 4 Scout (109B) runs at 22 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.8s. Meta's 109B Llama 4 Scout MoE model with a 10M-token context window.

Speed
22
tok/s
First Token
1.8
seconds
RAM Needed
128
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Llama 4 Scout 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 second22 tok/s
Time to first token1.8s
QuantizationQ4_K_M
Minimum RAM128 GB
Recommended engineOllama
Parameters109B
Benchmark date2026-03

Q4_K_M 109B Ollama M5 Max

Setup Guide: Run Llama 4 Scout on M5 Max

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

ollama run llama4:scout

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 30 tok/s 1.3s 192 GB MLX

System Requirements

To run Llama 4 Scout on M5 Max you need:

Compare More Models

See how Llama 4 Scout stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard