Qwimi-4B-i1-GGUF is an open-weight model from Team Mradermacher, released under Apache License 2.0. Its published files total 48.0 GB.
weighted/imatrix quants of https://huggingface.co/Rumiii/Qwimi-4B For a convenient overview and download list, visit our model page for this model.
Model Card
By Team Mradermacher, published under apache-2.0, revision 91e1e5069bfb.
weighted/imatrix quants of https://huggingface.co/Rumiii/Qwimi-4B For a convenient overview and download list, visit our model page for this model. static quants are available at https://huggingface.co/mradermacher/Qwimi-4B-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: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 See…
Read Team Mradermacher's full model card
About
weighted/imatrix quants of https://huggingface.co/Rumiii/Qwimi-4B
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Qwimi-4B-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_S | 1.2 | for the desperate |
| GGUF | i1-IQ1_M | 1.2 | mostly desperate |
| GGUF | i1-IQ2_XXS | 1.3 | |
| GGUF | i1-IQ2_XS | 1.5 | |
| GGUF | i1-IQ2_S | 1.5 | |
| GGUF | i1-IQ2_M | 1.6 | |
| GGUF | i1-Q2_K_S | 1.7 | very low quality |
| GGUF | i1-Q2_K | 1.8 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 1.8 | lower quality |
| GGUF | i1-IQ3_XS | 1.9 | |
| GGUF | i1-Q3_K_S | 2.0 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 2.0 | beats Q3_K* |
| GGUF | i1-IQ3_M | 2.1 | |
| GGUF | i1-Q3_K_M | 2.2 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 2.3 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 2.4 | |
| GGUF | i1-Q4_0 | 2.5 | fast, low quality |
| GGUF | i1-IQ4_NL | 2.5 | prefer IQ4_XS |
| GGUF | i1-Q4_K_S | 2.5 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 2.6 | fast, recommended |
| GGUF | i1-Q4_1 | 2.7 | |
| GGUF | i1-Q5_K_S | 2.9 | |
| GGUF | i1-Q5_K_M | 3.0 | |
| GGUF | i1-Q6_K | 3.4 | 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/Qwimi-4B-i1-GGUF
- Publisher
- Team Mradermacher
- Task
- Not stated by the source
- Modality
- Other
- Library
- transformers
- Parameters
- Not stated by the source
- Languages
- en
- Revision
- 91e1e5069bfbf6873cb49d26ce78d29288dd0364
- First published
- 2026-10-04
- Last updated
- 2026-10-05
Files and Weights
27 files, 48.0 GB in total. The weights are 25 files totalling 48.0 GB in gguf.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| Qwimi-4B.i1-IQ1_M.gguf | Weights | 1.1 GB | b8a92c3c7133 |
| Qwimi-4B.i1-IQ1_S.gguf | Weights | 1.1 GB | aace54737ce7 |
| Qwimi-4B.i1-IQ2_M.gguf | Weights | 1.5 GB | 0a7a23043b0e |
| Qwimi-4B.i1-IQ2_S.gguf | Weights | 1.4 GB | 5ed9edffa1a7 |
| Qwimi-4B.i1-IQ2_XS.gguf | Weights | 1.4 GB | 76a75f2d61f2 |
| Qwimi-4B.i1-IQ2_XXS.gguf | Weights | 1.2 GB | 365b18260ccb |
| Qwimi-4B.i1-IQ3_M.gguf | Weights | 2.0 GB | 94c4a6a89bae |
| Qwimi-4B.i1-IQ3_S.gguf | Weights | 1.9 GB | 4f9c4b5fbfa1 |
| Qwimi-4B.i1-IQ3_XS.gguf | Weights | 1.8 GB | aa79f818b8dc |
| Qwimi-4B.i1-IQ3_XXS.gguf | Weights | 1.7 GB | 8737c98ab487 |
| Qwimi-4B.i1-IQ4_NL.gguf | Weights | 2.4 GB | df8a5b77d106 |
| Qwimi-4B.i1-IQ4_XS.gguf | Weights | 2.3 GB | 2674d5aa8936 |
| Qwimi-4B.i1-Q2_K.gguf | Weights | 1.7 GB | 39dfacc6e1d5 |
| Qwimi-4B.i1-Q2_K_S.gguf | Weights | 1.6 GB | dd1fba92456f |
| Qwimi-4B.i1-Q3_K_L.gguf | Weights | 2.2 GB | 14fae989f0a3 |
| Qwimi-4B.i1-Q3_K_M.gguf | Weights | 2.1 GB | e9aa8dd6d560 |
| Qwimi-4B.i1-Q3_K_S.gguf | Weights | 1.9 GB | 1dc0c22416aa |
| Qwimi-4B.i1-Q4_0.gguf | Weights | 2.4 GB | 60b90eff628f |
| Qwimi-4B.i1-Q4_1.gguf | Weights | 2.6 GB | 28bc9c406931 |
| Qwimi-4B.i1-Q4_K_M.gguf | Weights | 2.5 GB | d27aa09a4bdc |
| Qwimi-4B.i1-Q4_K_S.gguf | Weights | 2.4 GB | c104152475d9 |
| Qwimi-4B.i1-Q5_K_M.gguf | Weights | 2.9 GB | d8683eecdb41 |
| Qwimi-4B.i1-Q5_K_S.gguf | Weights | 2.8 GB | fcf12fe2197e |
| Qwimi-4B.i1-Q6_K.gguf | Weights | 3.3 GB | effdcea88a7d |
| Qwimi-4B.imatrix.gguf | Weights | 3.9 MB | a3fcec9f5372 |
| README.md | Documentation | 5.6 KB | — |
| .gitattributes | Repository | 3.0 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 48.0 GB
Released by Team Mradermacher through its official repository on Hugging Face. Read the license.
Built From
- Derived from Rumiii/Qwimi-4B
- Quantized from Rumiii/Qwimi-4B
- Trained on (disclosed) Agent-Ark/Toucan-1.5M
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 48.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About Qwimi-4B-i1-GGUF
Can I use Qwimi-4B-i1-GGUF commercially?
Yes. Qwimi-4B-i1-GGUF is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.