QW

Qwen3-235B-A22B

QwenGGUF by unslothUpdated 2025-06-08
Download on Hugging Face
Parameters235B
Context40K
Layers94
Architectureqwen3moe
Smallest quant85.7 GB
Quick answer

Qwen3-235B-A22B needs about 144.2 GB of memory at Q4_K_M (a 142.2 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 19 quants, from 85.7 GB (Q2_K) to 470.3 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 6.3 GB.

Qwen3-235B-A22B – a 235 B parameter MoE language model with 22 B active experts

Qwen3-235B-A22B is a causal language model with 235 B total parameters and 22 B active parameters. It supports a native context length of 32,768 tokens and 131,072 tokens with YaRN. The model is released under the Apache‑2.0 license.

Good at

  • Advanced reasoning and math
  • Efficient instruction following
  • Agent tool integration

Limits

  • Requires large VRAM for full precision
  • No vision or multimodal support
  • Limited to text only

Best for

  • Complex code generation
  • Long‑form reasoning tasks
  • Agent‑based tool use

Who it’s for. Developers and researchers needing a high‑capacity MoE model for text‑only inference. The model is suitable for environments that can accommodate its memory demands and support llama.cpp or similar runtimes.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K85.7 GB (2 parts) 87.8 GB
Too big Get file →
Q2_K_L85.8 GB (2 parts) 87.9 GB
Too big Get file →
Q2_K_XL88.0 GB (2 parts) 90.1 GB
Too big Get file →
Q3_K_S101.4 GB (3 parts) 103.5 GB
Too big Get file →
Q3_K_XL103.7 GB (3 parts) 105.8 GB
Too big Get file →
Q3_K_M112.4 GB (3 parts) 114.5 GB
Too big Get file →
IQ4_XS125.5 GB (3 parts) 127.6 GB
Too big Get file →
Q4_K_S133.7 GB (3 parts) 135.8 GB
Too big Get file →
Q4_K_XL134.1 GB (3 parts) 136.2 GB
Too big Get file →
Q4_K_M142.2 GB (3 parts) 144.2 GB
Too big Get file →
Q4_1147.2 GB (3 parts) 149.3 GB
Too big Get file →
Q5_K_S161.9 GB (4 parts) 164.0 GB
Too big Get file →
Q5_K_M166.8 GB (4 parts) 168.9 GB
Too big Get file →
Q5_K_XL166.9 GB (4 parts) 169.0 GB
Too big Get file →
Q6_K193.0 GB (4 parts) 195.1 GB
Too big Get file →
Q6_K_XL198.9 GB (4 parts) 200.9 GB
Too big Get file →
Q8_0249.9 GB (6 parts) 252.0 GB
Too big Get file →
Q8_K_XL265.1 GB (6 parts) 267.2 GB
Too big Get file →
BF16470.3 GB (10 parts) 472.4 GB
Too big Get file →

For 8 GB VRAM, use Q4_K_S or Q4_K_M; for 16 GB VRAM, Q5_K_S or Q5_K_M; for 32 GB VRAM, Q6_K or Q6_K_XL. Memory estimates are approximate and based on 8 k context size.

What GPU do you need for Qwen3-235B-A22B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

Which Qwen3-235B-A22B quant should you choose?

Q4_K_M is the usual starting point for Qwen3-235B-A22B: it balances file size and quality well. Here it is a 142.2 GB file.

The Q8_0 file is 249.9 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is Q2_K at 85.7 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen3moe
Parameters235B (approximate, mixture of experts)
Active parameters22B
Layers94
Trained context40,960 tokens
KV cache (fp16)188 KB per token

Source

Quantized byunsloth
FamilyQwen
Licenseapache-2.0
Downloads (HF)11,243
Last updated2025-06-08

Frequently asked questions about Qwen3-235B-A22B

How much VRAM does Qwen3-235B-A22B need?

About 144.2 GB at Q4_K_M with an 8K context window. That is the 142.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Qwen3-235B-A22B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 87.8 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_K is 85.7 GB, Q2_K_L is 85.8 GB, Q2_K_XL is 88.0 GB, Q3_K_S is 101.4 GB, Q3_K_XL is 103.7 GB, Q3_K_M is 112.4 GB and 13 more.

What context length does Qwen3-235B-A22B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.6 GB at 8K and 6.3 GB at 32K.

Where can I download Qwen3-235B-A22B GGUF?

The files are on Hugging Face in the unsloth/Qwen3-235B-A22B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Qwen3-235B-A22B use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Qwen3-235B-A22B on 8 GB VRAM?

Only with a low‑precision quant such as Q4_K_S or Q4_K_M, which use about 136 GB of memory at 8 k context, so 8 GB VRAM is insufficient for full inference.

Does this model support image input?

No, Qwen3-235B-A22B is a text‑only model and does not include vision capabilities.

What license applies to this model?

The model is released under the Apache‑2.0 license, allowing free use and modification.

Other GGUFs of Qwen3-235B-A22B

Similar models

Browse all →

More from unsloth

All by unsloth →

More Qwen models

All Qwen →

Other large models

All large models →