Yes — with 27.1 GB to spare

Qwen3.6 35B-A3B at Q4_K_M fits your M3 Max · 64 GB entirely in unified memory at 8K context, at an estimated 56 tokens per second. There is room for its full 256K window.

Fully in unified memory 8K context Q4_K_M · 20.2 GB Apache 2.0 Released 16 Apr 2026 Vision

Mixture of experts with ~3B active: the fastest serious model a 24 GB card runs, and the best MoE under 40B on agentic coding.

What hardware do I need for Qwen3.6 35B-A3B? →

The VRAM budget

weights 20.2 GB

Weights 20.2 GB KV cache @ 8K 0.16 GB Runtime overhead 0.6 GB Free 27.1 GB of 48.0 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	35.5 GB	36.3 GB	256K	32	−0.1% ppl	Long context
Q6_K	27.4 GB	28.2 GB	256K	41	−0.4% ppl	Long context
Q5_K_M	23.7 GB	24.5 GB	256K	48	−0.8% ppl	Long context
Q4_K_M	20.2 GB	20.9 GB	256K	56	−1.9% ppl	Recommended
Q3_K_M	16.3 GB	17.1 GB	256K	69	−5.4% ppl	Long context
Q2_K	14.0 GB	14.8 GB	256K	81	−15% ppl	Long context

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it. Only 10 of its 40 blocks keep a per-token KV cache; the rest are linear-attention, Mamba or convolution blocks with a fixed-size state.

How to run it

Ollama llama.cpp LM Studio MLX

terminal

$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3.6-35B-A3B-4bit \
    --max-tokens 512 --prompt "Hello"

Apple's own array framework. The fastest path on Apple Silicon. More on MLX.

01Download is 20.2 GB. Keep it on an SSD — a first load off a spinning disk takes minutes.

02macOS caps what the GPU may wire down at about 48.0 GB of 64 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03There is room to go to the model's full 256K context on this card.

See all models for this rig Compare with another model