Qwable 9B Claude Fable 5 Heretic I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Model source
- Kind
- Other
- File size
- 4.91 MB–6.85 GB
- Base model
- richardyoung/Qwable-9B-Claude-Fable-5-heretic
- Version
- vRevision 6ca5a10
- Updated
- Oct 3, 2026
- Publisher
- @mradermacher
- Downloads
- 2.9K
- Parameters
- 9B
- Source
- Hugging Face
Source description
About
weighted/imatrix quants of https://huggingface.co/richardyoung/Qwable-9B-Claude-Fable-5-heretic
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Qwable-9B-Claude-Fable-5-heretic-GGUF
This is a vision model - mmproj files (if any) will be in the static repository.
Usage
If you are unsure how to use GGUF files, refer to one of TheBloke's READMEs for more details, including on how to concatenate multi-part files.
Provided Quants
(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.1 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 2.8 | for the desperate |
| GGUF | i1-IQ1_M | 3.0 | mostly desperate |
| GGUF | i1-IQ2_XXS | 3.2 | |
| GGUF | i1-IQ2_XS | 3.4 | |
| GGUF | i1-IQ2_S | 3.5 | |
| GGUF | i1-IQ2_M | 3.7 | |
| GGUF | i1-Q2_K_S | 3.8 | very low quality |
| GGUF | i1-Q2_K | 3.9 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 4.0 | lower quality |
| GGUF | i1-IQ3_XS | 4.3 | |
| GGUF | i1-Q3_K_S | 4.4 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 4.5 | beats Q3_K* |
| GGUF | i1-IQ3_M | 4.5 | |
| GGUF | i1-Q3_K_M | 4.7 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 5.0 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 5.3 | |
| GGUF | i1-Q4_0 | 5.4 | fast, low quality |
| GGUF | i1-Q4_K_S | 5.5 | optimal size/speed/quality |
| GGUF | i1-IQ4_NL | 5.5 | prefer IQ4_XS |
| GGUF | i1-Q4_K_M | 5.7 | fast, recommended |
| GGUF | i1-Q4_1 | 5.9 | |
| GGUF | i1-Q5_K_S | 6.4 | |
| GGUF | i1-Q5_K_M | 6.6 | |
| GGUF | i1-Q6_K | 7.5 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
image.png
And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9
FAQ / Model Request
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
Thanks
I thank my company, nethype GmbH, for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. Additional thanks to @nicoboss for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
Sources
1 source
Sources
1 sourceVerified Oct 3
Model artifacts
25 artifacts
Model artifacts
25 artifactsQwable-9B-Claude-Fable-5-heretic.i1-IQ1_M.gguf
gguf · 2.68 GB · SHA-256 06b506128b19…3dc5 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ1_S.gguf
gguf · 2.55 GB · SHA-256 2273b64b8378…ad42 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ2_M.gguf
gguf · 3.36 GB · SHA-256 25088ecf1fa2…238e · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ2_S.gguf
gguf · 3.19 GB · SHA-256 eb74009aa044…b276 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ2_XS.gguf
gguf · 3.06 GB · SHA-256 3cbfb6d16e1b…ee33 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ2_XXS.gguf
gguf · 2.89 GB · SHA-256 6947f6c80f0a…5598 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ3_M.gguf
gguf · 4.11 GB · SHA-256 eb07e6720166…9e4b · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ3_S.gguf
gguf · 4.07 GB · SHA-256 d33686122677…c689 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ3_XS.gguf
gguf · 3.95 GB · SHA-256 abe884f66108…6205 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ3_XXS.gguf
gguf · 3.67 GB · SHA-256 cc232b11238a…ef24 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ4_NL.gguf
gguf · 5.05 GB · SHA-256 47424d8d8828…6a6a · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-IQ4_XS.gguf
gguf · 4.84 GB · SHA-256 469d846e97ff…b4d5 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q2_K_S.gguf
gguf · 3.44 GB · SHA-256 d5586b137c4f…81a4 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q2_K.gguf
gguf · 3.56 GB · SHA-256 904eb4f8a55b…21c3 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q3_K_L.gguf
gguf · 4.59 GB · SHA-256 4fed97ecfcf2…0ab8 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q3_K_M.gguf
gguf · 4.31 GB · SHA-256 2cc2da0faa49…c2e7 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q3_K_S.gguf
gguf · 3.97 GB · SHA-256 f795a6fe366a…19cb · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q4_0.gguf
gguf · 4.96 GB · SHA-256 5d8b13c600d7…80a9 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q4_1.gguf
gguf · 5.41 GB · SHA-256 503c8dc0dcf5…1c7b · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q4_K_M.gguf
gguf · 5.24 GB · SHA-256 0922961de46b…8121 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q4_K_S.gguf
gguf · 4.98 GB · SHA-256 2aff2a82d16b…78b7 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q5_K_M.gguf
gguf · 6.02 GB · SHA-256 6b073be03be2…81cf · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q5_K_S.gguf
gguf · 5.87 GB · SHA-256 90724c213d6e…eb1a · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.i1-Q6_K.gguf
gguf · 6.85 GB · SHA-256 d129f5f1652f…e6b8 · Hugging Face
DownloadQwable-9B-Claude-Fable-5-heretic.imatrix.gguf
gguf · 4.91 MB · SHA-256 a2daf85f2045…a6da · Hugging Face
DownloadSource excerpts
3 excerpts
Source excerpts
3 excerpts--- base_model: richardyoung/Qwable-9B-Claude-Fable-5-heretic datasets: - Glint-Research/Fable-5-traces - Roman1111111/gpt5.5-terminal language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - qwen3.5 - sft - full-fine-tune - distillation - trl - agentic-coding - heretic - uncensored - decensored - abliterated - reproducible --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> <!-- ### quants: Q2_K IQ3_M Q4_K_S IQ3_XXS Q3_K_M small-IQ4_NL Q4_K_M IQ2_M Q6_K IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS Q5_K_S IQ2_S IQ1_S Q5_K_M Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> weighted/imatrix quants of https://huggingface.co/richardyoung/Qwable-9B-Claude-Fable-5-heretic <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwable-9B-Claude-Fable-5-heretic-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Qwable-9B-Claude-Fable-5-heretic-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Qwable-9B-Claude-Fable-5-heretic-GGUF).** ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Qwable-9B-Claude-Fable-5-heretic-i1-GGUF/resolve/main/Qwable-9B-Claude-Fable-5-heretic.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Qwable-9B-Claude-Fable-5-heretic-i1-GGUF/resolve/main/Qwable-9B-Claude-Fable-5-heretic.i1-IQ1_S.gguf) | i1-IQ1_S | 2.8 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Qwable-9B-Claude-Fable-5-heretic-i1-GGUF/resolve/main/Qwable-9B-Claude-Fable-5-heretic.i1-IQ1_M.gguf) | i1-IQ1_M | 3.0 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Qwable-9B...
Source context: 2920 downloads · 6 likes · Library transformers · Repo mradermacher/Qwable-9B-Claude-Fable-5-heretic-i1-GGUF
Source context: 5419 downloads · 4 likes · Library transformers · Repo mradermacher/Qwable-9B-Claude-Fable-5-heretic-i1-GGUF
