Skip to content
localmodel.run

Text model · Qwen3

Qwen3 235B A22B: RAM and VRAM requirements

Qwen3 235B A22B needs about 136.9 GB to run at Q4_K_M (the Q4_K_M GGUF file is ~132.39 GB to download; KV cache and overhead add the rest), or about 237.3 GB at Q8_0. The lightest hardware that runs it is Apple M3 Ultra (256GB).

Qwen3 family · 235B params (Mixture-of-Experts: activates only 22B of 235B params per token, so generation is faster than the total size suggests) · released Apr 2025.

Shopping for hardware? See what runs Qwen3 235B A22B →

License Apache-2.0 · Commercial OK ↓ 703K/mo ♥ 1.1K on HuggingFace
Q4_K_M GGUF
132.39 GB
Q8_0 GGUF
232.77 GB
Memory @ Q4 (4k)
~136.9 GB
Context
128 k

Q4_K_M and Q8_0 are GGUF download (file) sizes. Memory @ Q4 includes the KV cache and overhead, so it runs larger than the file on disk.

Will it run on your device?

Qwen3 235B A22B runs on 1 of 40 tracked devices at Q4_K_M.

1 run well 0 tight fit 39 too small
Fit check Q4_K_M
No, not enough memory
needs 136.9 GB usable 10.5 GB
See the full breakdown

Memory breakdown

Weights (Q4_K_M)132.39 GB
+
KV cache (4k)3.7 GB
+
Overhead0.8 GB
=
Total136.9 GB

How context length changes it

4k context ~136.9 GB 32k context ~162.6 GB 128k context ~250.9 GB

Longer context grows the KV cache, which for Qwen3 235B A22B is sized by its 22B active params, not the full 235B. It needs ~136.9 GB at 4k and ~250.9 GB at 128k.

Benchmark scores

Aider polyglot · coding

#2 of 10 ranked · Percent of 225 Exercism exercises solved across six languages.

59.6%

Sourced third-party benchmarks for the full-precision Qwen3 235B A22B, not a specific quant. See the full leaderboard.

Quantization sizes

GGUF quantson disk
Quantization Size on disk
Q2_K 98.4 GB est
Q3_K_M 114.9 GB est
Q4_K_M (default) 132.39 GB
Q5_K_M 167.4 GB est
Q6_K 192.7 GB est
Q8_0 232.77 GB
FP16 470 GB est

Lower quant = smaller and faster, slightly lower quality. Q4_K_M is the common default.

Run it

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

Which devices can run Qwen3 235B A22B?

Apple Silicon Macs

RAM-only laptops

iPhone & iPad

Android

NVIDIA GPUs

AMD GPUs

Same job, different size

Pick by what fits your memory: step down to free up VRAM, or step up if you have headroom.

Next size down dots.llm1 142B Next size up DeepSeek-V4-Flash 284B

Similar models

Head-to-head

FAQ

How much VRAM or RAM does Qwen3 235B A22B need?

At Q4_K_M, Qwen3 235B A22B needs about 136.9 GB (weights ~132.39 GB + KV cache + overhead) at a 4k context. At Q8_0 budget ~237.3 GB.

What is the Q4_K_M GGUF file size of Qwen3 235B A22B?

The Q4_K_M GGUF file is about 132.39 GB to download, and the Q8_0 GGUF is about 232.77 GB. That is the weights file on disk; to run it you also need room for the KV cache and overhead, so budget ~136.9 GB of memory at Q4_K_M.

Can Qwen3 235B A22B run on a laptop?

Qwen3 235B A22B is large; you need a high-memory Mac or multi-GPU setup at Q4_K_M.

Is Qwen3 235B A22B cheaper to run because it is a MoE model?

It is faster, not lighter. Qwen3 235B A22B activates only 22B of 235B params per token (so it runs quickly), but all experts must stay in memory, so it still needs memory for the full 235B.

Can I use Qwen3 235B A22B commercially?

Yes. Qwen3 235B A22B is licensed Apache-2.0, which permits commercial use.

Understand the numbers

Short guides to the ideas behind Qwen3 235B A22B's memory and quant figures.

Qwen3 235B sparse MoE (22B active). Q4_K_M ~132GB, fits a 192GB Mac. Size from the unsloth GGUF repo, exact-matched to the Ollama 235B tag.

Sources

Last validated 2026-08-03. Memory figures are estimates. See methodology.