QW

Qwen3.6 27B Fable 5 Experimental

QwenGGUF by TeichAIUpdated 2026-06-23
Download on Hugging Face
Parameters27.3B
Context256K
Layers65
Architectureqwen35
Smallest quant12.9 GB
Quick answer

Qwen3.6 27B Fable 5 Experimental needs about 20.1 GB of memory at Q4_K_M (a 17.4 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 8 quants, from 12.9 GB (Q3_K_S) to 54.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.

Qwen3.6 27B Fable 5 Experimental – a fine‑tuned planner and 3D modeler

Qwen3.6 27B Fable 5 Experimental is a 27.3B‑parameter model fine‑tuned on a small fable 5 dataset. It retains strong reasoning, coding, tools, and vision abilities. The model is optimized for planning, 3D modeling in three.js, small game creation, and ML engineering.

Good at

  • Planning and strategy
  • 3D modeling in three.js
  • Small game development

Limits

  • Small dataset may cause regression on some tasks
  • No large‑scale vision support beyond basic detection
  • Requires 8k context for full memory estimates

Best for

  • Game designers needing quick 3D prototypes
  • ML engineers building small projects
  • Users needing a planner with fable 5 style

Who it’s for. Developers and researchers who want a Qwen3.6 model with fable 5 style and strong reasoning. It is suitable for those who can tolerate some regression due to limited training data.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_S12.9 GB 15.6 GB
Too big Get file →
Q3_K_M14.2 GB 16.8 GB
Too big Get file →
IQ4_NL16.7 GB 19.4 GB
Too big Get file →
Q4_K_M17.4 GB 20.1 GB
Too big Get file →
Q5_K_M20.1 GB 22.8 GB
Too big Get file →
Q6_K22.9 GB 25.6 GB
Too big Get file →
Q8_029.4 GB 32.1 GB
Too big Get file →
BF1654.7 GB 57.3 GB
Too big Get file →

For 8 GB VRAM use Q3_K_S (12.92 GB, 15.6 GB memory) or Q3_K_M (14.15 GB, 16.8 GB memory). For 12 GB VRAM use Q4_K_M (17.4 GB, 20.1 GB memory). For 16 GB VRAM use Q5_K_M (20.08 GB, 22.8 GB memory).

What GPU do you need for Qwen3.6 27B Fable 5 Experimental?

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 Q3_K_S (12.9 GB file, about 15.6 GB in use).
  • 24 GB VRAM: the best quant that fits is Q5_K_M (20.1 GB file, about 22.8 GB in use).
  • 32 GB VRAM: the best quant that fits is Q6_K (22.9 GB file, about 25.6 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_0 (29.4 GB file, about 32.1 GB in use).

Which Qwen3.6 27B Fable 5 Experimental quant should you choose?

Q4_K_M is the usual starting point for Qwen3.6 27B Fable 5 Experimental: it balances file size and quality well. Here it is a 17.4 GB file.

The Q8_0 file is 29.4 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 Q3_K_S at 12.9 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

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 byTeichAI
FamilyQwen
Licenseapache-2.0
Downloads (HF)849
Last updated2026-06-23

Frequently asked questions about Qwen3.6 27B Fable 5 Experimental

How much VRAM does Qwen3.6 27B Fable 5 Experimental need?

About 20.1 GB at Q4_K_M with an 8K context window. That is the 17.4 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 Fable 5 Experimental on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 15.6 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Qwen3.6 27B Fable 5 Experimental GGUF?

It depends on the quant: Q3_K_S is 12.9 GB, Q3_K_M is 14.2 GB, IQ4_NL is 16.7 GB, Q4_K_M is 17.4 GB, Q5_K_M is 20.1 GB, Q6_K is 22.9 GB and 2 more.

What context length does Qwen3.6 27B Fable 5 Experimental 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 Fable 5 Experimental GGUF?

The files are on Hugging Face in the TeichAI/Qwen3.6-27B-Fable-5-Experimental-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 Fable 5 Experimental 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 Qwen3.6 27B Fable 5 on 8 GB VRAM?

Yes, using Q3_K_S or Q3_K_M quantizations. Estimated memory at 8k context is 15.6 GB or 16.8 GB respectively.

Does this model support vision tasks?

It has basic vision abilities but is not a full vision model. Use it for simple image recognition or analysis.

What license applies to this model?

The model is released under apache-2.0 license.

Other GGUFs of Qwen3.6-27B-Fable-5-Experimental

Similar models

Browse all →

More from TeichAI

All by TeichAI →

More Qwen models

All Qwen →

Other medium models

All medium models →