RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

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

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K)13.5 GB Fits13.6 GB Fits14.1 GB Fits15.9 GB Fits356
3-bit (Q3_K_M) •16.9 GB Fits17.0 GB Fits17.4 GB Fits19.3 GB Fits280
4-bit (Q4_K_M) •22.1 GB Fits22.1 GB Fits22.6 GB Fits24.5 GB Fits212
5-bit (Q5_K_M) •26.2 GB Fits26.3 GB Fits26.7 GB Fits28.6 GB Fits177
6-bit (Q6_K) •28.9 GB Fits29.0 GB Fits29.4 GB Fits31.3 GB Fits160
8-bit (Q8_0) •36.2 GB Fits36.2 GB Fits36.7 GB Fits38.6 GB Fits127
16-bit (F16/BF16) •67.1 GB Tight67.2 GB Tight67.7 GB Tight69.6 GB Tight67

• 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.