Yes — Qwen 4 4B (4B) runs at 108 tok/s on M4 Pro with 24 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.3s. A capable open-source LLM with 4B parameters.
LLMCheck measured Qwen 4 4B on M4 Pro 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 | 108 tok/s |
| Time to first token | 0.3s |
| Quantization | Q4_K_M |
| Minimum RAM | 24 GB |
| Recommended engine | Ollama |
| Parameters | 4B |
| Benchmark date | 2026-06 |
Q4_K_M 4B Ollama M4 Pro
The recommended engine for Qwen 4 4B on M4 Pro is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~24 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 135 tok/s | 0.2s | 128 GB | MLX |
| M3 | 85 tok/s | 0.3s | 16 GB | MLX |
| M2 | 62 tok/s | 0.4s | 8 GB | Ollama |
| M1 | 45 tok/s | 0.6s | 8 GB | Ollama |
To run Qwen 4 4B on M4 Pro you need:
See how Qwen 4 4B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard