Darwin 28B REASON I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Modellquelle
- Art
- Other
- Dateigröße
- 13,0 MB–20,6 GB
- Basismodell
- FINAL-Bench/Darwin-28B-REASON
- Version
- vRevision bc5873d
- Aktualisiert
- 15. Okt. 2026
- Verleger
- @mradermacher
- Downloads
- 655
- Parameter
- 28B
- Quelle
- Hugging Face
Quellenbeschreibung
About
weighted/imatrix quants of https://huggingface.co/FINAL-Bench/Darwin-28B-REASON
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Darwin-28B-REASON-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 | 7.2 | for the desperate |
| GGUF | i1-IQ1_M | 7.7 | mostly desperate |
| GGUF | i1-IQ2_XXS | 8.5 | |
| GGUF | i1-IQ2_XS | 9.2 | |
| GGUF | i1-IQ2_S | 9.5 | |
| GGUF | i1-IQ2_M | 10.1 | |
| GGUF | i1-Q2_K_S | 10.3 | very low quality |
| GGUF | i1-Q2_K | 10.8 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 11.3 | lower quality |
| GGUF | i1-IQ3_XS | 12.1 | |
| GGUF | i1-Q3_K_S | 12.2 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 12.5 | beats Q3_K* |
| GGUF | i1-IQ3_M | 12.7 | |
| GGUF | i1-Q3_K_M | 13.4 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 14.4 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 15.2 | |
| GGUF | i1-Q4_0 | 15.6 | fast, low quality |
| GGUF | i1-Q4_K_S | 15.7 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 16.6 | fast, recommended |
| GGUF | i1-Q4_1 | 17.2 | |
| GGUF | i1-Q5_K_S | 18.8 | |
| GGUF | i1-Q5_K_M | 19.3 | |
| GGUF | i1-Q6_K | 22.2 | 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.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 7. Aug.
Modellartefakte
24 Artefakte
Modellartefakte
24 ArtefakteDarwin-28B-REASON.i1-IQ1_M.gguf
gguf · 7,11 GB · SHA-256 895f1dceea2a…f514 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ1_S.gguf
gguf · 6,66 GB · SHA-256 8b125d9f4408…a0df · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ2_M.gguf
gguf · 9,32 GB · SHA-256 8eb770eb1663…5173 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ2_S.gguf
gguf · 8,72 GB · SHA-256 261ce0bc2807…9b23 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ2_XS.gguf
gguf · 8,47 GB · SHA-256 6d841984f386…f660 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ2_XXS.gguf
gguf · 7,85 GB · SHA-256 d6e20e9eea0c…39d4 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ3_M.gguf
gguf · 11,7 GB · SHA-256 8ff339dcdd3b…00dc · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ3_S.gguf
gguf · 11,6 GB · SHA-256 8dfe1e210656…745b · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ3_XS.gguf
gguf · 11,1 GB · SHA-256 a42f913640eb…31e6 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ3_XXS.gguf
gguf · 10,4 GB · SHA-256 37be99c4a988…8c2d · Hugging Face
HerunterladenDarwin-28B-REASON.i1-IQ4_XS.gguf
gguf · 14,0 GB · SHA-256 cbdcb94c2ad8…6a4a · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q2_K_S.gguf
gguf · 9,54 GB · SHA-256 842cd10af072…5c2f · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q2_K.gguf
gguf · 9,98 GB · SHA-256 fc682695f530…69b7 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q3_K_L.gguf
gguf · 13,4 GB · SHA-256 3a53ead9555c…16ae · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q3_K_M.gguf
gguf · 12,4 GB · SHA-256 fed76b728ddd…bea5 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q3_K_S.gguf
gguf · 11,2 GB · SHA-256 20fb49e19e92…ea11 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q4_0.gguf
gguf · 14,5 GB · SHA-256 0691cf7fcbac…e1a0 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q4_1.gguf
gguf · 15,9 GB · SHA-256 1d9bd1877e8a…38f5 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q4_K_M.gguf
gguf · 15,4 GB · SHA-256 1e86f797e72a…d946 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q4_K_S.gguf
gguf · 14,5 GB · SHA-256 5fe6a112ab8d…4287 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q5_K_M.gguf
gguf · 17,9 GB · SHA-256 b81b7dd63ca4…32e4 · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q5_K_S.gguf
gguf · 17,4 GB · SHA-256 55d59e75ada7…523d · Hugging Face
HerunterladenDarwin-28B-REASON.i1-Q6_K.gguf
gguf · 20,6 GB · SHA-256 6b0d11753b6d…84c9 · Hugging Face
HerunterladenDarwin-28B-REASON.imatrix.gguf
gguf · 13,0 MB · SHA-256 61d559b67ce9…f99a · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: FINAL-Bench/Darwin-28B-REASON language: - en - zh - ko - ja - multilingual library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - darwin - darwin-reason - reasoning - advanced-reasoning - chain-of-thought - thinking - reasoning-trace-distillation - rtd - darwin-delphi - test-time-compute - qwen3.6 - qwen - gpqa - benchmark - open-source - apache-2.0 - proto-agi - vidraft - eval-results --- ## 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: 1 --> weighted/imatrix quants of https://huggingface.co/FINAL-Bench/Darwin-28B-REASON <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Darwin-28B-REASON-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Darwin-28B-REASON-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Darwin-28B-REASON-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/Darwin-28B-REASON-i1-GGUF/resolve/main/Darwin-28B-REASON.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Darwin-28B-REASON-i1-GGUF/resolve/main/Darwin-28B-REASON.i1-IQ1_S.gguf) | i1-IQ1_S | 7.2 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Darwin-28B-REASON-i1-GGUF/resolve/main/Darwin-28B-REASON.i1-IQ1_M.gguf) | i1-IQ1_M | 7.7 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Darwin-28B-REASON-i1-GGUF/resolve/main/Darwin-28B-REASON.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.5...
Source context: 655 downloads · 21 likes · Library transformers · Repo mradermacher/Darwin-28B-REASON-i1-GGUF
Source context: 677 downloads · 18 likes · Library transformers · Repo mradermacher/Darwin-28B-REASON-i1-GGUF
