Run Hermes 4 70B on M5 Max

Yes — Hermes 4 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

tok/s

First Token

1.8

seconds

RAM Needed

128

GB minimum

Engine

MLX

recommended

Benchmark Details

LLMCheck measured Hermes 4 70B 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	16 tok/s
Time to first token	1.8s
Quantization	Q4_K_M
Minimum RAM	128 GB
Recommended engine	MLX
Parameters	70B
Benchmark date	2026-05

Q4_K_M 70B MLX M5 Max

Setup Guide: Run Hermes 4 70B on M5 Max

The recommended engine for Hermes 4 70B on M5 Max is MLX. Install with pip and pull the model:

pip install mlx-lm

mlx_lm.generate --model mlx-community/hermes-4-70b-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run hermes-4-70b

Performance on Other Apple Silicon Chips

Chip	Speed	First Token	Min RAM	Engine
M4 Ultra	18 tok/s	1.5s	192 GB	Ollama
M4 Max	13 tok/s	2.1s	128 GB	MLX

System Requirements

To run Hermes 4 70B 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 Hermes 4 70B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard