Run Grok 4 Open on M4 Ultra

Yes — Grok 4 Open (100B) runs at 40 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via MLX. First token latency is 0.8s. A capable open-source LLM with 100B parameters.

Speed
40
tok/s
First Token
0.8
seconds
RAM Needed
192
GB minimum
Engine
MLX
recommended
Want to run Grok 4 Open faster — or step up to bigger models? Find your Mac →

Benchmark Details

The LLMCheck index estimates Grok 4 Open on M4 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 →

MetricValue
Tokens per second40 tok/s
Time to first token0.8s
QuantizationQ4_K_M
Minimum RAM192 GB
Recommended engineMLX
Parameters100B
Benchmark date2026-06

Q4_K_M 100B MLX M4 Ultra

Setup Guide: Run Grok 4 Open on M4 Ultra

The recommended engine for Grok 4 Open on M4 Ultra is MLX. Install with pip and pull the model:

pip install mlx-lm
mlx_lm.generate --model mlx-community/grok-4-open-q4_k_m --prompt "Hello!"

Alternatively, you can use Ollama for a simpler setup:

ollama run grok-4-open

Performance on Other Apple Silicon Chips

ChipSpeedFirst TokenMin RAMEngine
M5 Max 32 tok/s 1.0s 128 GB MLX
M5 Max 28 tok/s 1.2s 64 GB Ollama

System Requirements

To run Grok 4 Open on M4 Ultra you need:

🛒 Get a Mac that runs Grok 4 Open

Grok 4 Open needs about 192 GB of unified memory. These current Apple Silicon Macs have the headroom to run it comfortably:

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

Compare More Models

See how Grok 4 Open stacks up against other models on your specific Mac hardware.

Open Compare Tool Full Leaderboard