Open-weight model
DeepSeek-R1-0528-Qwen3-8B-heretic-i1-GGUF
by Team Mradermacher mradermacher/DeepSeek-R1-0528-Qwen3-8B-heretic-i1-GGUF
DeepSeek-R1-0528-Qwen3-8B-heretic-i1-GGUF is an open-weight model from Team Mradermacher, released under MIT License. Its published files total 96.4 GB.
weighted/imatrix quants of https://huggingface.co/richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic For a convenient overview and download list, visit our model page for this model.
Model Card
By Team Mradermacher, published under mit, revision 2745be1307b6.
weighted/imatrix quants of https://huggingface.co/richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF 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. (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) Here is a handy graph by ikawrakow comparing some lower-quality quant And here are Artefact2's thoughts on the matter…
Read Team Mradermacher's full model card
About
weighted/imatrix quants of https://huggingface.co/richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/DeepSeek-R1-0528-Qwen3-8B-heretic-GGUF
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_M | 2.4 | mostly desperate |
| GGUF | i1-IQ2_XXS | 2.6 | |
| GGUF | i1-IQ2_XS | 2.8 | |
| GGUF | i1-IQ2_M | 3.2 | |
| GGUF | i1-Q2_K_S | 3.2 | very low quality |
| GGUF | i1-Q2_K | 3.4 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 3.5 | lower quality |
| GGUF | i1-Q3_K_S | 3.9 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 4.0 | |
| GGUF | i1-Q3_K_M | 4.2 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 4.5 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 4.7 | |
| GGUF | i1-IQ4_NL | 4.9 | prefer IQ4_XS |
| GGUF | i1-Q4_K_S | 4.9 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 5.1 | fast, recommended |
| GGUF | i1-Q5_K_S | 5.8 | |
| GGUF | i1-Q6_K | 6.8 | practically like static Q6_K |
Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):
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.
Identity and Version
- Repository
- mradermacher/DeepSeek-R1-0528-Qwen3-8B-heretic-i1-GGUF
- Publisher
- Team Mradermacher
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 2745be1307b62e375a9ec8d1a3fa198bdee20fc5
- First published
- 2026-09-30
- Last updated
- 2026-09-30
Files and Weights
27 files, 96.4 GB in total. The weights are 25 files totalling 96.4 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ1_M.gguf | Weights | 2.3 GB | d965ead2eb06 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ1_S.gguf | Weights | 2.1 GB | 2a43aead4660 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ2_M.gguf | Weights | 3.1 GB | 28c156196d76 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ2_S.gguf | Weights | 2.9 GB | 7e7d4c421223 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ2_XS.gguf | Weights | 2.7 GB | 4d469f4b223e |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ2_XXS.gguf | Weights | 2.5 GB | 1f8a7a93be8d |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ3_M.gguf | Weights | 3.9 GB | 4bcace8871b2 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ3_S.gguf | Weights | 3.8 GB | 1c7ca9aa6f1a |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ3_XS.gguf | Weights | 3.6 GB | eb32c49ac32e |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ3_XXS.gguf | Weights | 3.4 GB | 107a936f65d0 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ4_NL.gguf | Weights | 4.8 GB | 3e6c31797dad |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-IQ4_XS.gguf | Weights | 4.6 GB | cecfeaf44ab2 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q2_K.gguf | Weights | 3.3 GB | d5c86450587e |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q2_K_S.gguf | Weights | 3.1 GB | a47bfdde937c |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q3_K_L.gguf | Weights | 4.4 GB | 8fcef4ee97f7 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q3_K_M.gguf | Weights | 4.1 GB | cf3bc0609859 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q3_K_S.gguf | Weights | 3.8 GB | ca2a796e5b98 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q4_0.gguf | Weights | 4.8 GB | 21ba9040b96a |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q4_1.gguf | Weights | 5.2 GB | af92e2e7392a |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q4_K_M.gguf | Weights | 5.0 GB | e5a828b6866a |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q4_K_S.gguf | Weights | 4.8 GB | ad9d018b4942 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q5_K_M.gguf | Weights | 5.9 GB | a6cafab357d0 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q5_K_S.gguf | Weights | 5.7 GB | cb9d5ca451be |
| DeepSeek-R1-0528-Qwen3-8B-heretic.i1-Q6_K.gguf | Weights | 6.7 GB | c414f525a036 |
| DeepSeek-R1-0528-Qwen3-8B-heretic.imatrix.gguf | Weights | 5.3 MB | ad7beabdab98 |
| README.md | Documentation | 5.7 KB | — |
| .gitattributes | Repository | 3.6 KB | — |
License and Download
- License
- mit
- Access
- Open weights, no gate
- Download size
- 96.4 GB
Released by Team Mradermacher through its official repository on Hugging Face. Read the license.
Built From
- Derived from richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic
- Quantized from richardyoung/DeepSeek-R1-0528-Qwen3-8B-heretic
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 96.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About DeepSeek-R1-0528-Qwen3-8B-heretic-i1-GGUF
Can I use DeepSeek-R1-0528-Qwen3-8B-heretic-i1-GGUF commercially?
Yes. DeepSeek-R1-0528-Qwen3-8B-heretic-i1-GGUF is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.