SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled needs about 19.5 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 20 quants, from 12.0 GB (Q2_K_XL) to 54.7 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 8.7 GB.
SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled – 27.3B Qwen model fine‑tuned for efficient coding and reasoning
SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled is a 27.3B parameter Qwen model. It is fine‑tuned from ThinkingCap-Qwen3.6-27B and distilled with 1,000 curated reasoning sequences. The model supports coding and reasoning tasks with a 262,144 token context window.
Good at
- Efficient coding with self‑narration
- Adaptive chain‑of‑thought reasoning
- Large context handling
Limits
- No vision support
- Requires large VRAM for higher quant levels
- License is Apache‑2.0
Best for
- Developing code with real‑time debugging
- Complex reasoning tasks in a single prompt
- Research on efficient LLM finetuning
Who it’s for. Engineers and researchers who need a large language model that can reason and code efficiently. The model is suitable for developers building AI‑assisted coding tools or conducting research on chain‑of‑thought techniques.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K_XL | 12.0 GB | 14.7 GB | Too big | Get file → | |
| Q3_K_S | 12.3 GB | 14.9 GB | Too big | Get file → | |
| IQ3_S | 12.6 GB | 15.3 GB | Too big | Get file → | |
| Q3_K_M | 13.5 GB | 16.2 GB | Too big | Get file → | |
| Q3_K_XL | 14.7 GB | 17.4 GB | Too big | Get file → | |
| IQ4_XS | 15.3 GB | 18.0 GB | Too big | Get file → | |
| Q4_K_S | 15.8 GB | 18.5 GB | Too big | Get file → | |
| IQ4_NL | 16.0 GB | 18.7 GB | Too big | Get file → | |
| IQ4_NL | 16.0 GB | 18.7 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.5 GB | Too big | Get file → | |
| Q4_K_XL | 17.9 GB | 20.6 GB | Too big | Get file → | |
| Q5_K_S | 19.0 GB | 21.7 GB | Too big | Get file → | |
| Q5_K_M | 19.5 GB | 22.2 GB | Too big | Get file → | |
| Q5_K_XL | 20.3 GB | 23.0 GB | Too big | Get file → | |
| Q6_K | 22.4 GB | 25.1 GB | Too big | Get file → | |
| Q6_K_XL | 26.0 GB | 28.7 GB | Too big | Get file → | |
| MXFP4_MOE | 29.0 GB | 31.7 GB | Too big | Get file → | |
| Q8_0 | 29.0 GB | 31.7 GB | Too big | Get file → | |
| Q8_K_XL | 35.8 GB | 38.5 GB | Too big | Get file → | |
| BF16 | 54.7 GB | 57.3 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K_XL (12 GB file, 14.7 GB memory). For 12 GB VRAM, Q3_K_S (12.26 GB file, 14.9 GB memory). For 16 GB VRAM, Q4_K_S (15.83 GB file, 18.5 GB memory). Higher quant levels require proportionally more VRAM.
What GPU do you need for SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled?
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 IQ3_S (12.6 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_XL (20.3 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is MXFP4_MOE (29.0 GB file, about 31.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_K_XL (35.8 GB file, about 38.5 GB in use).
Which SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled quant should you choose?
Q4_K_M is the usual starting point for SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled: it balances file size and quality well. Here it is a 16.8 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 Q2_K_XL at 12.0 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
Source
Frequently asked questions about SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled
How much VRAM does SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled need?
About 19.5 GB at Q4_K_M with an 8K context window. That is the 16.8 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 SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 14.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled GGUF?
It depends on the quant: Q2_K_XL is 12.0 GB, Q3_K_S is 12.3 GB, IQ3_S is 12.6 GB, Q3_K_M is 13.5 GB, Q3_K_XL is 14.7 GB, IQ4_XS is 15.3 GB and 14 more.
What context length does SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled 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 SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled GGUF?
The files are on Hugging Face in the mfielding92/SmartCode-Fable-5-CoT-Reasoning-QKVO-Qwen-3.6-27B-Distilled repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SmartCode Fable 5 CoT Reasoning QKVO Qwen 3.6 27B Distilled 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 this model on 8 GB VRAM?
Yes, the Q2_K_XL quant requires 14.7 GB memory at 8k context, which fits within 8 GB VRAM when using llama.cpp with appropriate batching.
Does the model support image inputs?
No, the model has no vision capabilities and only processes text.
What license applies to this model?
The model is released under the Apache‑2.0 license.