Yes — Ministral 3 14B (14B) runs at 30 tok/s on M3 with 16 GB RAM using Q4_K_M quantization via LM Studio. First token latency is 1.2s. A capable open-source LLM with 14B parameters.
Want to run Ministral 3 14B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Ministral 3 14B on M3 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 | 1.2s |
| Quantization | Q4_K_M |
| Minimum RAM | 16 GB |
| Recommended engine | LM Studio |
| Parameters | 14B |
| Benchmark date | 2026-01 |
Q4_K_M 14B LM Studio M3
The recommended engine for Ministral 3 14B on M3 is LM Studio. Install Ollama, then pull the model:
Ollama handles quantization automatically — it will download the Q4_K_M variant (~16 GB) and start an interactive chat session.
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M5 Max | 58 tok/s | 0.7s | 64 GB | Ollama |
| M4 Pro | 40 tok/s | 0.9s | 24 GB | Ollama |
To run Ministral 3 14B on M3 you need:
Ministral 3 14B needs about 16 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 Ministral 3 14B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard