QW

Qwen3.8-27B

QwenGGUF by FenomAIUpdated 2026-08-15
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant9.0 GB
Quick answer

Qwen3.8-27B needs about 19.8 GB of memory at Q4_K_M (a 17.1 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 22 quants, from 9.0 GB (IQ2_XXS) to 54.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Qwen3.8-27B – 27.3B parameter vision‑language model

Qwen3.8-27B is a 27.3B parameter dense model with native vision‑language support. It is built on the Qwen3.5 architecture and offers improved coding, professional work, research, and agentic tasks. The model is released under the apache‑2.0 license.

Good at

  • Vision‑language understanding
  • Tool‑calling and reasoning
  • Long‑horizon agentic tasks

Limits

  • No separate vision model required
  • Requires at least 8k context for full functionality
  • No GPU‑only inference for very large quants

Best for

  • Image‑based code review
  • Multimodal document summarization
  • Agentic task planning with tool usage

Who it’s for. Developers and researchers needing a compact, deployment‑friendly vision‑language model. The model is suitable for local inference with llama.cpp or other GGUF‑compatible frameworks.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS9.0 GB 11.7 GB
Too big Get file →
IQ2_M10.3 GB 13.0 GB
Too big Get file →
Q2_K_XL10.7 GB 13.4 GB
Too big Get file →
IQ3_XXS11.9 GB 14.6 GB
Too big Get file →
Q3_K_S12.6 GB 15.3 GB
Too big Get file →
Q3_K_XL13.4 GB 16.1 GB
Too big Get file →
Q3_K_M13.8 GB 16.5 GB
Too big Get file →
IQ4_XS15.7 GB 18.4 GB
Too big Get file →
Q4_016.1 GB 18.7 GB
Too big Get file →
Q4_K_S16.1 GB 18.8 GB
Too big Get file →
IQ4_NL16.3 GB 19.0 GB
Too big Get file →
Q4_K_M17.1 GB 19.8 GB
Too big Get file →
Q4_117.5 GB 20.2 GB
Too big Get file →
Q4_K_XL17.9 GB 20.6 GB
Too big Get file →
Q5_K_S19.3 GB 22.0 GB
Too big Get file →
Q5_K_M19.8 GB 22.5 GB
Too big Get file →
Q5_K_XL20.2 GB 22.9 GB
Too big Get file →
Q6_K22.9 GB 25.6 GB
Too big Get file →
Q6_K_XL25.9 GB 28.6 GB
Too big Get file →
Q8_029.0 GB 31.7 GB
Too big Get file →
Q8_K_XL31.5 GB 34.1 GB
Too big Get file →
BF1654.7 GB (2 parts) 57.3 GB
Too big Get file →

For 8‑GB VRAM use IQ2_XXS (9.01 GB, 11.7 GB memory at 8k context) or Q2_K_XL (10.68 GB, 13.4 GB memory). For 16‑GB VRAM use Q4_K_M (17.11 GB, 19.8 GB memory) or Q5_K_M (19.83 GB, 22.5 GB memory). Larger quants require more VRAM and RAM as shown in the file list.

What GPU do you need for Qwen3.8-27B?

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: the best quant that fits is IQ2_XXS (9.0 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_S (12.6 GB file, about 15.3 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_XL (20.2 GB file, about 22.9 GB in use).
  • 32 GB VRAM: the best quant that fits is Q8_0 (29.0 GB file, about 31.7 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (31.5 GB file, about 34.1 GB in use).

Which Qwen3.8-27B quant should you choose?

Q4_K_M is the usual starting point for Qwen3.8-27B: it balances file size and quality well. Here it is a 17.1 GB file.

The Q8_0 file is 29.0 GB, about 1.7 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 IQ2_XXS at 9.0 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

Architectureqwen35
Parameters27.3B
Layers65
Trained context262,144 tokens
KV cache (fp16)260 KB per token

Source

Quantized byFenomAI
FamilyQwen
Licenseapache-2.0
Downloads (HF)608
Last updated2026-08-15

Frequently asked questions about Qwen3.8-27B

How much VRAM does Qwen3.8-27B need?

About 19.8 GB at Q4_K_M with an 8K context window. That is the 17.1 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 Qwen3.8-27B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.8-27B GGUF?

It depends on the quant: IQ2_XXS is 9.0 GB, IQ2_M is 10.3 GB, Q2_K_XL is 10.7 GB, IQ3_XXS is 11.9 GB, Q3_K_S is 12.6 GB, Q3_K_XL is 13.4 GB and 16 more.

What context length does Qwen3.8-27B support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.2 GB at 8K and 8.7 GB at 32K.

Where can I download Qwen3.8-27B GGUF?

The files are on Hugging Face in the FenomAI/Qwen3.8-27B-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 Qwen3.8-27B 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 Qwen3.8-27B on 8 GB VRAM?

Yes, with a low‑bit quant such as IQ2_XXS or Q2_K_XL, which use about 11.7–13.4 GB memory at 8k context.

Does the model support vision tasks?

Yes, it is a native vision‑language model that understands images and videos.

What license applies to this model?

The model is released under the apache‑2.0 license.

Other GGUFs of Qwen3.8-27B

Similar models

Browse all →

More from FenomAI

All by FenomAI →

More Qwen models

All Qwen →

Other medium models

All medium models →