Skip to content
localmodel.run

text model · Qwen3 · macOS

Can I run Qwen3 235B A22B on Apple M3 Ultra (256GB)?

Compatibility verdict VRAM threshold engine
Yes, it runsGPU accelerated

Yes. Qwen3 235B A22B runs on Apple M3 Ultra (256GB) at Q4_K_M (~136.9 GB of ~192 GB usable).

Needs ~136.9 GB Device usable ~192 GB

Runs at Q4_K_M using ~136.9 GB of ~192 GB usable.

Q4_K_M needed
~136.9 GB
Usable on device
~192 GB
Device memory
256 GB
Best quant
Q4_K_M

Run it

Install commands macOS

Pick your tool. All three load the same Q4_K_M weights.

Ollama
$ ollama run qwen3:235b
llama.cpp
$ llama-cli -hf unsloth/Qwen3-235B-A22B-GGUF:Q4_K_M
LM Studio
$ lms get unsloth/Qwen3-235B-A22B-GGUF

vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.

Model Qwen3
Parameters
235B (MoE, 22B active)
Q4_K_M size
132.39 GB
Context
128k
Ollama tag
qwen3:235b
Full Qwen3 235B A22B requirements →
Device macOS
Memory
256 GB unified
Usable for weights
~192 GB
Best runtime
MLX direct / Ollama (MLX backend)
Best models for Apple M3 Ultra (256GB) →

You could also run

FAQ

Can Apple M3 Ultra (256GB) run Qwen3 235B A22B?

Yes. Qwen3 235B A22B runs on Apple M3 Ultra (256GB) at Q4_K_M (~136.9 GB of ~192 GB usable).

How much memory does Qwen3 235B A22B need?

Apple M3 Ultra (256GB) has room to spare. At Q4_K_M the weights are ~132.39 GB; with KV cache and runtime overhead, budget ~136.9 GB at a 4k context. It is a Mixture-of-Experts model (235B total / 22B active), so all experts must stay in memory; memory tracks total params, not active params.

What is the best tool to run Qwen3 235B A22B on macOS?

LM Studio for a simple setup; mlx-lm for the most speed. vLLM is NOT a Mac tool, it is a CUDA/Linux serving engine. Unified memory is not a fixed VRAM slice; ~70% is usable for weights.

Sources

Memory figures are estimates. See methodology.