Run Llama 5 Scout on M5 Max

Yes — Llama 5 Scout (109B) runs at 42 tok/s on M5 Max with 128 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.8s. A capable open-source LLM with 109B parameters.

Speed

tok/s

First Token

0.8

seconds

RAM Needed

128

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured Llama 5 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.

Metric	Value
Tokens per second	42 tok/s
Time to first token	0.8s
Quantization	Q4_K_M
Minimum RAM	128 GB
Recommended engine	MLX
Parameters	109B
Benchmark date	2026-05

Q4_K_M 109B MLX M5 Max

Setup Guide: Run Llama 5 Scout on M5 Max

The recommended engine for Llama 5 Scout on M5 Max is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/llama-5-scout-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run llama-5-scout

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M4 Ultra	50 tok/s	0.6s	192 GB	MLX
M4 Max	35 tok/s	0.9s	128 GB	MLX

System Requirements

To run Llama 5 Scout on M5 Max you need:

• Mac with M5 Max chip (or newer)
• 128 GB unified memory minimum
• macOS 13 Ventura or later
• ~108-128 GB free disk space for the model file
• MLX installed (see our Ollama install guide)

Compare More Models

See how Llama 5 Scout stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard