No — not on this device

Qwen3 235B-A22B at Q4_K_M needs 134.2 GB against 10.7 GB usable, and the shortfall of 123.5 GB is more than 32 GB of system RAM can cover at a tolerable speed. A smaller sibling or a lower quantisation is the honest answer here.

Does not fit 8K context Q4_K_M · 132.1 GB Apache 2.0 Released Apr 2025

Workstation class. Realistically a 192 GB unified-memory or multi-GPU model.

What hardware do I need for Qwen3 235B-A22B? →

Fits instead: Qwen3 14B (10.2 GB) · Qwen3 8B (6.3 GB)

The VRAM budget

weights 132.1 GB

Weights 132.1 GB KV cache @ 8K 1.47 GB Runtime overhead 0.6 GB Over budget 123.5 GB past 10.7 GB

Quantisation ladder

Quant	Weights	Total @ 8K	Max context	Tok/s	Quality	Fit
Q8_0	232.5 GB	234.6 GB	—	~0.8	−0.1% ppl	223.9 GB over
Q6_K	179.5 GB	181.5 GB	—	~1.1	−0.4% ppl	170.8 GB over
Q5_K_M	155.1 GB	157.2 GB	—	~1.2	−0.8% ppl	146.5 GB over
Q4_K_M	132.1 GB	134.2 GB	—	~1.4	−1.9% ppl	123.5 GB over
Q3_K_M	107.0 GB	109.0 GB	—	~1.8	−5.4% ppl	98.3 GB over
Q2_K	91.6 GB	93.7 GB	—	~2.1	−15% ppl	83.0 GB over

Quality is the published perplexity delta against f16 weights. Max context assumes an f16 KV cache; q8_0 roughly doubles it.

How to run it

Ollama llama.cpp LM Studio MLX

terminal

$ pip install mlx-lm
$ mlx_lm.generate --model mlx-community/Qwen3-235B-A22B-4bit \
    --max-tokens 512 --prompt "Hello"

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

01Download is 132.1 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 10.7 GB of 16 GB. Raising it with iogpu.wired_limit_mb is possible, and risky.

03If it falls back to CPU silently, drop the context first, then step down a quantisation.

See all models for this rig Compare with another model