Can Qwen3.6 35B A3B run on the Mac M2 Max 96GB?
Yes. At 8K context the best fit is Q8_0, using about 36.2 GB of the 72.0 GB usable on the Mac M2 Max 96GB. Estimated speed ceiling: ~127 tokens/sec.
Memory by quant and context
| Quant | 4K ctx | 8K ctx | 32K ctx | 128K ctx | Max tok/s (est., 8K) |
|---|---|---|---|---|---|
| 2-bit (Q2_K) | 13.5 GB Fits | 13.6 GB Fits | 14.1 GB Fits | 15.9 GB Fits | 356 |
| 3-bit (Q3_K_M) • | 16.9 GB Fits | 17.0 GB Fits | 17.4 GB Fits | 19.3 GB Fits | 280 |
| 4-bit (Q4_K_M) • | 22.1 GB Fits | 22.1 GB Fits | 22.6 GB Fits | 24.5 GB Fits | 212 |
| 5-bit (Q5_K_M) • | 26.2 GB Fits | 26.3 GB Fits | 26.7 GB Fits | 28.6 GB Fits | 177 |
| 6-bit (Q6_K) • | 28.9 GB Fits | 29.0 GB Fits | 29.4 GB Fits | 31.3 GB Fits | 160 |
| 8-bit (Q8_0) • | 36.2 GB Fits | 36.2 GB Fits | 36.7 GB Fits | 38.6 GB Fits | 127 |
| 16-bit (F16/BF16) • | 67.1 GB Tight | 67.2 GB Tight | 67.7 GB Tight | 69.6 GB Tight | 67 |
• real GGUF file size from unsloth/Qwen3.6-35B-A3B-MTP-GGUF. Speed is a bandwidth ceiling (400 GB/s), not a benchmark. Methodology.
More
Qwen3.6 35B A3B on every GPU and Mac · Every model that runs on the Mac M2 Max 96GB · Apple Silicon guide · Try other settings in the calculator
Data: Hugging Face Hub (Qwen/Qwen3.6-35B-A3B), Apple specs. Data as of 2026-11-17.