QW

Qwen3.6 27B MTP

QwenGGUF by td-builderUpdated 2026-08-01
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant10.9 GB
Quick answer

Qwen3.6 27B MTP needs about 22.2 GB of memory at Q5_K (a 19.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 7 quants, from 10.9 GB (Q2_K) to 54.7 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Qwen3.6 27B MTP is a 27.3B-parameter Qwen model in GGUF format, quantized by td-builder. Its trained context length is 256K tokens. The repository has 7 quant files, from 10.9 GB (Q2_K) to 54.7 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K10.9 GB 13.5 GB
Too big Get file →
Q3_K13.5 GB 16.2 GB
Too big Get file →
Q4_K16.8 GB 19.5 GB
Too big Get file →
Q5_K19.5 GB 22.2 GB
Too big Get file →
Q6_K22.4 GB 25.1 GB
Too big Get file →
Q8_029.0 GB 31.7 GB
Too big Get file →
F1654.7 GB 57.3 GB
Too big Get file →

What GPU do you need for Qwen3.6 27B MTP?

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: the best quant that fits is Q2_K (10.9 GB file, about 13.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K (19.5 GB file, about 22.2 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_0 (29.0 GB file, about 31.7 GB in use).

Which Qwen3.6 27B MTP quant should you choose?

Q5_K (19.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.

If memory is tight, the smallest file is Q2_K at 10.9 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 bytd-builder
FamilyQwen
Licenseapache-2.0
Downloads (HF)98
Last updated2026-08-01

Frequently asked questions about Qwen3.6 27B MTP

How much VRAM does Qwen3.6 27B MTP need?

About 22.2 GB at Q5_K with an 8K context window. That is the 19.5 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 Qwen3.6 27B MTP on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 27B MTP GGUF?

It depends on the quant: Q2_K is 10.9 GB, Q3_K is 13.5 GB, Q4_K is 16.8 GB, Q5_K is 19.5 GB, Q6_K is 22.4 GB, Q8_0 is 29.0 GB and 1 more.

What context length does Qwen3.6 27B MTP 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 Qwen3.6 27B MTP GGUF?

The files are on Hugging Face in the td-builder/Qwen3.6-27B-MTP-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 Qwen3.6 27B MTP 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.

Other GGUFs of Qwen3.6-27B

Similar models

Browse all →

More from td-builder

All by td-builder →

More Qwen models

All Qwen →

Other medium models

All medium models →