Yes — Bonsai 27B (27B) runs at 12 tok/s on M2 with 8 GB RAM using 1-bit quantization via MLX. First token latency is 0.5s. A capable open-source LLM with 27B parameters.
Want to run Bonsai 27B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Bonsai 27B on M2 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 | 12 tok/s |
| Time to first token | 0.5s |
| Quantization | 1-bit |
| Minimum RAM | 8 GB |
| Recommended engine | MLX |
| Parameters | 27B |
| Benchmark date | 2026-08 |
1-bit 27B MLX M2
The recommended engine for Bonsai 27B on M2 is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
To run Bonsai 27B on M2 you need:
Bonsai 27B needs about 8 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 Bonsai 27B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard