ronaldcmz/Qwen3.5-9B-Fable-5-v1-GGUF overview
Qwen3.5 9B Claude Fable 5 This tune was more successful than anticipated... First 9B I've tested that was able to make an atari breakout game without bugs zero…
Runs locally from ~875.6 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Qwen3.5-9B-Fable-5-Distill.bf16.gguf | GGUF | GGUF | 16.69 GB | Download |
| Qwen3.5-9B-Fable-5-Distill.iq4_nl.gguf | GGUF | GGUF | 5.07 GB | Download |
| Qwen3.5-9B-Fable-5-Distill.q3_k_m.gguf | GGUF | GGUF | 4.31 GB | Download |
| Qwen3.5-9B-Fable-5-Distill.q3_k_s.gguf | GGUF | GGUF | 3.97 GB | Download |
| Qwen3.5-9B-Fable-5-Distill.q4_k_m.gguf | GGUF | GGUF | 5.24 GB | Download |
| Qwen3.5-9B-Fable-5-Distill.q5_k_m.gguf | GGUF | GGUF | 6.02 GB | Download |
| Qwen3.5-9B-Fable-5-Distill.q6_k.gguf | GGUF | GGUF | 6.85 GB | Download |
| Qwen3.5-9B-Fable-5-Distill.q8_0.gguf | GGUF | GGUF | 8.87 GB | Download |
| mmproj-BF16.gguf | GGUF | BF16 | 879.0 MB | Download |
| mmproj-F16.gguf | GGUF | F16 | 875.6 MB | Download |
| mmproj-F32.gguf | GGUF | F32 | 1.70 GB | Download |
Model Details
Model README
---
base_model: TeichAI/Qwen3.5-9B-Fable-5-v1
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3_5
license: apache-2.0
language:
- en
datasets:
- armand0e/claude-fable-5-claude-code
---
Qwen3.5 9B - Claude Fable 5
This tune was more successful than anticipated... First 9B I've tested that was able to make an atari breakout game without bugs (zero-shot, q8)
arc arc/e boolq
Qwen3.5-9B-Fable-5-v1 0.624 0.806 0.891
Qwen3.5-9B 0.553 0.712 0.892As always big thanks to @nightmedia for the benchmarks :)
---
The data for this model was easily extracted, formatted, and masked for training with Teich <img src="https://cdn-avatars.huggingface.co/v1/production/uploads/6837935ac3b7ffe0d2559ce9/-AxyvV4wfUY8uo87kNKkK.png" width="20" height="20" style="display: inline-block; vertical-align: middle; margin: 0 3px;">
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Run ronaldcmz/Qwen3.5-9B-Fable-5-v1-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models