Yes — Maple Preview 20B-A1B (20B-A1B) runs at 200 tok/s on M4 with 16 GB RAM using Ternary quantization via MLX. First token latency is 0.1s. A capable open-source LLM with 20B-A1B parameters.
Want to run Maple Preview 20B-A1B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Maple Preview 20B-A1B on M4 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 | 200 tok/s |
| Time to first token | 0.1s |
| Quantization | Ternary |
| Minimum RAM | 16 GB |
| Recommended engine | MLX |
| Parameters | 20B-A1B |
| Benchmark date | 2026-08 |
Ternary 20B-A1B MLX M4
The recommended engine for Maple Preview 20B-A1B on M4 is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
To run Maple Preview 20B-A1B on M4 you need:
Maple Preview 20B-A1B 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 Maple Preview 20B-A1B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard