Qwable-Claude-Fable-5-Distilled-NPU2 needs about 11.1 GB of memory at Q8_0 (a 9.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
Qwable-Claude-Fable-5-Distilled-NPU2 – 8.95B parameter Qwen3.5‑based model
Qwable-Claude-Fable-5-Distilled-NPU2 is a distilled, full‑parameter fine‑tune of Qwen3.5‑9B. It focuses on reasoning, tool use, and multimodal vision inherited from the base. The model is released under apache‑2.0.
Good at
- Reasoning
- Tool use
- Vision (inherited)
Limits
- No vision fine‑tuning
- Large VRAM requirement
- No multilingual support
Best for
- Long coding tasks
- Agentic multi‑turn dialogues
- Tool‑augmented reasoning
Who it’s for. Developers needing a dense, multimodal assistant for coding and agentic tasks. The model is suitable for users with sufficient GPU memory to run the Q8_0 quantization.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 9.5 GB | 11.1 GB | Too big | Get file → |
The Q8_0 quantization is 9.53 GB and requires about 11.1 GB VRAM at 8 k context. For 8 GB VRAM, a lower‑bit quant such as Q4_K_M would be needed, but it is not available in this release. The current quant is best for GPUs with 12 GB or more.
What GPU do you need for Qwable-Claude-Fable-5-Distilled-NPU2?
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 Q8_0 (9.5 GB file, about 11.1 GB in use).
Which Qwable-Claude-Fable-5-Distilled-NPU2 quant should you choose?
Q8_0 (9.5 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Qwable-Claude-Fable-5-Distilled-NPU2
How much VRAM does Qwable-Claude-Fable-5-Distilled-NPU2 need?
About 11.1 GB at Q8_0 with an 8K context window. That is the 9.5 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 Qwable-Claude-Fable-5-Distilled-NPU2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Qwable-Claude-Fable-5-Distilled-NPU2 GGUF?
It depends on the quant: Q8_0 is 9.5 GB.
What context length does Qwable-Claude-Fable-5-Distilled-NPU2 support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download Qwable-Claude-Fable-5-Distilled-NPU2 GGUF?
The files are on Hugging Face in the Atomic-Germ/Qwable-Claude-Fable-5-Distilled-NPU2 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Qwable-Claude-Fable-5-Distilled-NPU2 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?
The Q8_0 quant requires 11.1 GB VRAM at 8 k context, so 8 GB VRAM is insufficient.
Does the model support vision tasks?
Vision behavior is inherited from the base model but was not tuned or tested.
What license applies to this model?
The model is licensed under apache‑2.0, inherited from the base weights.