Yes — Devstral Small 24B (24B) runs at 26 tok/s on M4 Pro with 32 GB RAM using Q4_K_M quantization via Ollama. First token latency is 1.0s. A capable open-source LLM with 24B parameters.
LLMCheck measured Devstral Small 24B 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 | 26 tok/s |
| Time to first token | 1.0s |
| Quantization | Q4_K_M |
| Minimum RAM | 32 GB |
| Recommended engine | Ollama |
| Parameters | 24B |
| Benchmark date | 2026-05 |
Q4_K_M 24B Ollama M4 Pro
The recommended engine for Devstral Small 24B on M4 Pro is Ollama. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~32 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 45 tok/s | 0.6s | 128 GB | MLX |
| M5 Max | 38 tok/s | 0.7s | 64 GB | Ollama |
| M4 Max | 35 tok/s | 0.8s | 48 GB | MLX |
To run Devstral Small 24B on M4 Pro you need:
See how Devstral Small 24B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard