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.
- Downloads last month
- 595
GGUF
Model size
35B params
Architecture
qwen35moe
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Trilogix1/Anthropics-Fable-finetuned-in-Qwen3.6-35B
Base model
Qwen/Qwen3.6-35B-A3B Finetuned
lordx64/Qwable-v1