Yes — Llama 4 Scout (109B) runs at 30 tok/s on M4 Ultra with 192 GB RAM using Q4_K_M quantization via MLX. First token latency is 1.3s. Meta's 109B Llama 4 Scout MoE model with a 10M-token context window.
Want to run Llama 4 Scout faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Llama 4 Scout 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 →
| Metric | Value |
|---|---|
| Tokens per second | 30 tok/s |
| Time to first token | 1.3s |
| Quantization | Q4_K_M |
| Minimum RAM | 192 GB |
| Recommended engine | MLX |
| Parameters | 109B |
| Benchmark date | 2026-02 |
Q4_K_M 109B MLX M4 Ultra
The recommended engine for Llama 4 Scout on M4 Ultra is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 26 tok/s | 1.5s | 128 GB | MLX |
| M5 Max | 22 tok/s | 1.8s | 128 GB | Ollama |
To run Llama 4 Scout on M4 Ultra you need:
Llama 4 Scout 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.
See how Llama 4 Scout stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard