Run Hermes 4 70B on M4 Ultra

Yes — Hermes 4 70B (70B) runs at 18 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.5s. A capable open-source LLM with 70B parameters.

Speed
18
tok/s
First Token
1.5
seconds
RAM Needed
192
GB minimum
Engine
Ollama
recommended

Benchmark Details

LLMCheck measured Hermes 4 70B on M4 Ultra 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 second18 tok/s
Time to first token1.5s
QuantizationQ4_K_M
Minimum RAM192 GB
Recommended engineOllama
Parameters70B
Benchmark date2026-05

Q4_K_M 70B Ollama M4 Ultra

Setup Guide: Run Hermes 4 70B on M4 Ultra

The recommended engine for Hermes 4 70B on M4 Ultra is Ollama. Install Ollama, then pull the model:

ollama run hermes-4-70b

Ollama handles quantization automatically — it will download the Q4_K_M variant (~192 GB) and start an interactive chat session.

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 16 tok/s 1.8s 128 GB MLX
M4 Max 13 tok/s 2.1s 128 GB MLX

System Requirements

To run Hermes 4 70B on M4 Ultra you need:

Compare More Models

See how Hermes 4 70B stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard