RunsOnMy ModelsGPUs & MacsBy VRAMAPI pricesVRAM calculatorNew

Can Qwen3.5 35B A3B run on the Mac M2 Max 96GB?

Yes. At 8K context the best fit is Q8_0, using about 35.4 GB of the 72.0 GB usable on the Mac M2 Max 96GB. Estimated speed ceiling: ~130 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) •16.2 GB Fits16.3 GB Fits16.7 GB Fits18.6 GB Fits293
4-bit (Q4_K_M) •21.5 GB Fits21.5 GB Fits22.0 GB Fits23.9 GB Fits218
5-bit (Q5_K_M) •25.4 GB Fits25.5 GB Fits25.9 GB Fits27.8 GB Fits183
6-bit (Q6_K) •27.8 GB Fits27.9 GB Fits28.4 GB Fits30.2 GB Fits166
8-bit (Q8_0) •35.3 GB Fits35.4 GB Fits35.9 GB Fits37.7 GB Fits130
16-bit (F16/BF16) •65.6 GB Tight65.6 GB Tight66.1 GB Tight68.0 GB Tight69

• real GGUF file size from unsloth/Qwen3.5-35B-A3B-GGUF. Speed is a bandwidth ceiling (400 GB/s), not a benchmark. Methodology.

More

Qwen3.5 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/Qwen3.5-35B-A3B), Apple specs. Data as of 2026-11-17.