QW

Qwen3 32B 108B A32B

QwenGGUF by mradermacherUpdated 2026-11-11
Download on Hugging Face
Parameters108B
Context40K
Layers64
Architectureqwen3moe
Smallest quant39.7 GB
Quick answer

Qwen3 32B 108B A32B needs about 42.3 GB of memory at Q2_K (a 39.7 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 2 quants, from 39.7 GB (Q2_K) to 46.8 GB (Q3_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 8.6 GB.

Qwen3 32B 108B A32B is a 108B-parameter Qwen model in GGUF format, quantized by mradermacher. Its trained context length is 40K tokens. The repository has 2 quant files, from 39.7 GB (Q2_K) to 46.8 GB (Q3_K_S).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K39.7 GB 42.3 GB
Too big Get file →
Q3_K_S46.8 GB 49.5 GB
Too big Get file →

What GPU do you need for Qwen3 32B 108B A32B?

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: the best quant that fits is Q2_K (39.7 GB file, about 42.3 GB in use).

Which Qwen3 32B 108B A32B quant should you choose?

Q2_K (39.7 GB) is the middle option in this repository. 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
Parameters108B (approximate, mixture of experts)
Active parameters32B
Layers64
Trained context40,960 tokens
KV cache (fp16)256 KB per token

Source

Quantized bymradermacher
FamilyQwen
Downloads (HF)73
Last updated2026-11-11

Frequently asked questions about Qwen3 32B 108B A32B

How much VRAM does Qwen3 32B 108B A32B need?

About 42.3 GB at Q2_K with an 8K context window. That is the 39.7 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 32B 108B A32B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 42.3 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3 32B 108B A32B GGUF?

It depends on the quant: Q2_K is 39.7 GB, Q3_K_S is 46.8 GB.

What context length does Qwen3 32B 108B A32B support?

The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 2.1 GB at 8K and 8.6 GB at 32K.

Where can I download Qwen3 32B 108B A32B GGUF?

The files are on Hugging Face in the mradermacher/Qwen3-32B-108B-A32B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Other GGUFs of Qwen3-32B-108B-A32B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Qwen models

All Qwen →

Other large models

All large models →