Gemma 4 31B Isometry RP I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Modellquelle
- Art
- Other
- Dateigröße
- 13,1 MB–24,5 GB
- Basismodell
- maldv/Gemma-4-31B-Isometry-RP
- Version
- vRevision feab9ab
- Aktualisiert
- 3. Okt. 2026
- Verleger
- @mradermacher
- Downloads
- 1945
- Parameter
- 31B
- Aufgaben
- Textgenerierung
- Quelle
- Hugging Face
Quellenbeschreibung
About
weighted/imatrix quants of https://huggingface.co/maldv/Gemma-4-31B-Isometry-RP
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-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 | 7.7 | for the desperate |
| GGUF | i1-IQ1_M | 8.3 | mostly desperate |
| GGUF | i1-IQ2_XXS | 9.2 | |
| GGUF | i1-IQ2_XS | 10.1 | |
| GGUF | i1-IQ2_S | 10.9 | |
| GGUF | i1-Q2_K_S | 11.5 | very low quality |
| GGUF | i1-IQ2_M | 11.6 | |
| GGUF | i1-Q2_K | 12.5 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 12.8 | lower quality |
| GGUF | i1-IQ3_XS | 13.8 | |
| GGUF | i1-IQ3_S | 14.5 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 15.1 | |
| GGUF | i1-Q3_K_M | 16.0 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 17.3 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 17.6 | |
| GGUF | i1-Q4_0 | 18.6 | fast, low quality |
| GGUF | i1-Q4_K_S | 18.7 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 19.6 | fast, recommended |
| GGUF | i1-Q4_1 | 20.5 | |
| GGUF | i1-Q5_K_S | 22.4 | |
| GGUF | i1-Q5_K_M | 22.9 | |
| GGUF | i1-Q6_K | 26.5 | 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.
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 3. Okt.
Modellartefakte
24 Artefakte
Modellartefakte
24 ArtefakteGemma-4-31B-Isometry-RP.i1-IQ1_M.gguf
gguf · 7,63 GB · SHA-256 9fb2d441465a…d2ba · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ1_S.gguf
gguf · 7,10 GB · SHA-256 3ca049d42c7a…5368 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ2_M.gguf
gguf · 10,7 GB · SHA-256 d84bbf5194a0…b446 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ2_S.gguf
gguf · 10,0 GB · SHA-256 093b4d928882…6bfb · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ2_XS.gguf
gguf · 9,31 GB · SHA-256 2e8f8a3e8061…ae0b · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ2_XXS.gguf
gguf · 8,51 GB · SHA-256 0659b836a81a…f53c · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ3_M.gguf
gguf · 14,0 GB · SHA-256 ceb9fbfdcd47…d689 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ3_S.gguf
gguf · 13,4 GB · SHA-256 08e7fe1bf00c…f75c · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ3_XS.gguf
gguf · 12,7 GB · SHA-256 6e9e9d689111…b712 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ3_XXS.gguf
gguf · 11,8 GB · SHA-256 a8029b3d3fb3…139c · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-IQ4_XS.gguf
gguf · 16,3 GB · SHA-256 7005b8972a0a…bd63 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q2_K_S.gguf
gguf · 10,7 GB · SHA-256 530874b2e7e1…e245 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q2_K.gguf
gguf · 11,5 GB · SHA-256 4de4a7629277…6065 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q3_K_L.gguf
gguf · 16,1 GB · SHA-256 c01edb21b64d…c926 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q3_K_M.gguf
gguf · 14,8 GB · SHA-256 7aaa2424c829…599b · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q3_K_S.gguf
gguf · 13,4 GB · SHA-256 c9e7c18a10c5…7a91 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q4_0.gguf
gguf · 17,2 GB · SHA-256 0fdbffb11b46…204e · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q4_1.gguf
gguf · 19,0 GB · SHA-256 d1cf66811b34…d0eb · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q4_K_M.gguf
gguf · 18,1 GB · SHA-256 c148e5c9ba3f…b10a · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q4_K_S.gguf
gguf · 17,3 GB · SHA-256 a9699d60d48e…6596 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q5_K_M.gguf
gguf · 21,2 GB · SHA-256 ff971eedef6c…cc37 · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q5_K_S.gguf
gguf · 20,8 GB · SHA-256 5b7025a32fa2…481b · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.i1-Q6_K.gguf
gguf · 24,5 GB · SHA-256 8fb1fed21b04…114f · Hugging Face
HerunterladenGemma-4-31B-Isometry-RP.imatrix.gguf
gguf · 13,1 MB · SHA-256 be0e64d7ecc5…c178 · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: maldv/Gemma-4-31B-Isometry-RP language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - gemma - gemma4 - merge - isometric-merge - roleplay - creative-writing - conversational - text-generation-inference --- ## 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/maldv/Gemma-4-31B-Isometry-RP <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma-4-31B-Isometry-RP-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-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/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.i1-IQ1_S.gguf) | i1-IQ1_S | 7.7 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.2 | | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-...
--- base_model: maldv/Gemma-4-31B-Isometry-RP language: - en library_name: transformers license: gemma mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - gemma - gemma4 - merge - isometric-merge - roleplay - creative-writing - conversational - text-generation-inference --- ## 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/maldv/Gemma-4-31B-Isometry-RP <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Gemma-4-31B-Isometry-RP-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-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/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.i1-IQ1_S.gguf) | i1-IQ1_S | 7.7 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.i1-IQ1_M.gguf) | i1-IQ1_M | 8.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isometry-RP.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.2 | | | [GGUF](https://huggingface.co/mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF/resolve/main/Gemma-4-31B-Isome...
Source context: 1945 downloads · 2 likes · Library transformers · Repo mradermacher/Gemma-4-31B-Isometry-RP-i1-GGUF
