---
license: other
license_name: hugston-licenced
license_link: LICENSE
datasets:
- lordx64/agentic-distill-fable-5-sft
base_model:
- lordx64/Qwable-v1
tags:
- qwen3.6
- fable
- anthropic
- finetuned
- hugston
- HugstonOne
- Quanta
- gguf
---
This is a converted and quantized version of Qwen 3.6 35B using Quanta and HugstonOne.

---

model size  = 132219.74 MiB (32.00 BPW)

---

quant size  = 21192.47 MiB (5.13 BPW)


Original weights here: https://huggingface.co/lordx64/Qwable-v1

---

# Credit to Qwen team for the model creation
# Credit to https://huggingface.co/lordx64/Qwable-v1 for the finetuning work
# Credit to LLama.cpp team for the great contribution
# Credit to Hugston Team for Converting, Quantizing, Testing, Benching and other...
# Credit to Huggingface for the amazing hosting platform

---



The quantization in GGUF was made in f32 for better quality quants.  
Here we show Quanta our convertor and Quantizer tool. 

![image](https://cdn-uploads.huggingface.co/production/uploads/6818be9259cb758d06603579/wmfqVJ6TtAmTIFtmnh12y.png)