Yes — Qwen 3.6-35B-A3B (35B-A3B) runs at 64 tok/s on M6 with 32 GB RAM using 4-bit quantization via MLX. Alibaba's flagship 35B MoE (3B active) with 73.4% SWE-bench Verified — the best local coding model.
Want to run Qwen 3.6-35B-A3B faster — or step up to bigger models? Find your Mac →The LLMCheck index estimates Qwen 3.6-35B-A3B on M6 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 | 64 tok/s |
| Time to first token | — |
| Quantization | 4-bit |
| Minimum RAM | 32 GB |
| Recommended engine | MLX |
| Parameters | 35B-A3B |
| Benchmark date | 2026-10 |
4-bit 35B-A3B MLX M6
The recommended engine for Qwen 3.6-35B-A3B on M6 is MLX. Install with pip and pull the model:
Alternatively, you can use Ollama for a simpler setup:
| Chip | Speed | First Token | Min RAM | Engine |
|---|---|---|---|---|
| M4 Max | 120 tok/s | — | 48 GB | MLX |
To run Qwen 3.6-35B-A3B on M6 you need:
Qwen 3.6-35B-A3B 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 the LLMCheck index free.
See how Qwen 3.6-35B-A3B stacks up against other models on your specific Mac hardware.
Open Compare Tool Full Leaderboard