Yes — Mistral Small 3.2 24B (24B) runs at 18 tok/s on M2 Max with 32 GB RAM using Q4_K_M quantization via Ollama. First token latency is 0.5s. A capable open-source LLM with 24B parameters.
Want to run Mistral Small 3.2 24B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Mistral Small 3.2 24B on M2 Max 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 | 18 tok/s |
| Time to first token | 0.5s |
| Quantization | Q4_K_M |
| Minimum RAM | 32 GB |
| Recommended engine | Ollama |
| Parameters | 24B |
| Benchmark date | 2026-08 |
Q4_K_M 24B Ollama M2 Max
The recommended engine for Mistral Small 3.2 24B on M2 Max 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 | 42 tok/s | 0.7s | 64 GB | Ollama |
| M4 Max | 38 tok/s | 0.8s | 48 GB | MLX |
| M4 Pro | 28 tok/s | 1.0s | 32 GB | Ollama |
To run Mistral Small 3.2 24B on M2 Max you need:
Mistral Small 3.2 24B needs about 32 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 Mistral Small 3.2 24B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard