Yes, just — 3.1 GB spare

Qwen3.6 35B-A3B at Q4_K_M fits your M2 Pro · 32 GB entirely in unified memory at 8K context, at an estimated 28 tokens per second. Past 164K the KV cache pushes it over — quantise the cache to q8_0, or step down a quantisation, to go longer.

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.

Hardware requirements What hardware do I need to run Qwen3.6 35B-A3B? →

At Q4_K_M with an 8K context: a 32 GB GPU (RTX 5090) or a 36 GB Mac (M4 Max). Minimum, recommended, high-quality and long-context tiers, with all 114 devices checked at every quantisation.

The VRAM budget

weights 20.2 GB
Weights 20.2 GB KV cache @ 8K 0.16 GB Runtime overhead 0.6 GB Free 3.1 GB of 24.0 GB

Quantisation ladder

QuantWeightsTotal @ 8KMax contextTok/sQualityFit
Q8_0 35.5 GB 36.3 GB — ~16 −0.1% ppl 12.3 GB over
Q6_K 27.4 GB 28.2 GB — ~21 −0.4% ppl 4.2 GB over
Q5_K_M 23.7 GB 24.5 GB — ~24 −0.8% ppl 0.5 GB over
Q4_K_M 20.2 GB 20.9 GB 164K 28 −1.9% ppl Recommended
Q3_K_M 16.3 GB 17.1 GB 256K 35 −5.4% ppl Long context
Q2_K 14.0 GB 14.8 GB 256K 41 −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

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 24.0 GB of 32 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.
03Only 3.1 GB is spare, so a long system prompt can still push it over. Its real ceiling here is 164K context.
See all models for this rig Compare with another model

Related models on an M2 Pro · 32 GB

ModelTotalTok/s est.
Qwen3.6 27B
27.8B · same family
Q4_K_M · 16.7 GB 7.1 Runs great
Ornith 1.5 35B-A3B
35.9B MoE · similar size
Q4_K_M · 20.9 GB 28 Tight fit
LLM-jp 4 33B Thinking
33.2B · similar size
Q4_K_M · 21.3 GB 6.0 Tight fit
Qwen3 32B
32.8B · similar size
Q4_K_M · 21.0 GB 6.1 Tight fit
DeepSeek-R1-Distill-Qwen 32B
32.8B · similar size
Q4_K_M · 21.0 GB 6.1 Tight fit
Qwen2.5-Coder 32B
32.8B · similar size
Q4_K_M · 21.0 GB 6.1 Tight fit
Olmo 3.1 32B Instruct
32.2B · similar size
Q4_K_M · 20.0 GB 6.2 Runs great

Every model against the M2 Pro · 32 GB →

Qwen3.6 35B-A3B on other hardware

DeviceTotalTok/s est.
GeForce RTX 4060 Laptop
7.0 GB usable · 256 GB/s
20.9 GB — Won't fit
GeForce RTX 3060 12 GB
10.6 GB usable · 360 GB/s
20.9 GB ~13 CPU offload
M4 · 16 GB
10.7 GB usable · 120 GB/s
20.9 GB — Won't fit
GeForce RTX 4090
22.4 GB usable · 1008 GB/s
20.9 GB 126 Tight fit
Radeon RX 7900 XTX
22.4 GB usable · 960 GB/s
20.9 GB 120 Tight fit
GeForce RTX 5090
30.4 GB usable · 1792 GB/s
20.9 GB 225 Runs great
M4 Max · 36 GB
27.0 GB usable · 410 GB/s
20.9 GB 58 Runs great
M3 Max · 64 GB
48.0 GB usable · 400 GB/s
20.9 GB 56 Runs great

All 114 devices, by tier →