Gemma 4 31B It Qat Q4 0 Unquantized I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Modellquelle
- Art
- Other
- Dateigröße
- 13,1 MB–18,1 GB
- Basismodell
- google/gemma-4-31B-it-qat-q4_0-unquantized
- Version
- vRevision 5e59cc4
- Aktualisiert
- 3. Okt. 2026
- Verleger
- @mradermacher
- Downloads
- 1835
- Parameter
- 31B
- Quelle
- Hugging Face
Quellenbeschreibung
About
weighted/imatrix quants of https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized
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-it-qat-q4_0-unquantized-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 | 7.3 | for the desperate |
| GGUF | i1-IQ1_M | 7.8 | mostly desperate |
| GGUF | i1-IQ2_XXS | 8.8 | |
| GGUF | i1-IQ2_XS | 9.6 | |
| GGUF | i1-IQ2_S | 10.3 | |
| GGUF | i1-IQ2_M | 11.0 | |
| GGUF | i1-Q2_K_S | 11.1 | very low quality |
| GGUF | i1-Q2_K | 12.0 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 12.2 | lower quality |
| GGUF | i1-IQ3_XS | 13.2 | |
| GGUF | i1-IQ3_S | 13.9 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 13.9 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 14.5 | |
| GGUF | i1-Q3_K_M | 15.4 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 16.7 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 16.8 | |
| GGUF | i1-Q4_0 | 17.8 | fast, low quality |
| GGUF | i1-Q4_K_S | 17.9 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 18.8 | fast, recommended |
| GGUF | i1-Q4_1 | 19.6 |
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
21 Artefakte
Modellartefakte
21 Artefaktegemma-4-31B-it-qat-q4_0-unquantized.i1-IQ1_M.gguf
gguf · 7,20 GB · SHA-256 3aa5e0dddca6…db40 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ1_S.gguf
gguf · 6,67 GB · SHA-256 c703f46eaac9…c838 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ2_M.gguf
gguf · 10,2 GB · SHA-256 4d0486cf5629…b00c · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ2_S.gguf
gguf · 9,46 GB · SHA-256 21029198ec2e…0b94 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ2_XS.gguf
gguf · 8,88 GB · SHA-256 c989b32ab8ad…e824 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ2_XXS.gguf
gguf · 8,08 GB · SHA-256 f04b1ddbc7ac…3ff9 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ3_M.gguf
gguf · 13,4 GB · SHA-256 2a035f859fb2…eefa · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ3_S.gguf
gguf · 12,8 GB · SHA-256 33bbb264363c…5553 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ3_XS.gguf
gguf · 12,2 GB · SHA-256 97b988b62b3a…14f1 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ3_XXS.gguf
gguf · 11,2 GB · SHA-256 0dc76d666145…c675 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-IQ4_XS.gguf
gguf · 15,6 GB · SHA-256 8ae0ee4de923…24aa · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q2_K_S.gguf
gguf · 10,2 GB · SHA-256 58105fa2abd3…a01a · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q2_K.gguf
gguf · 11,1 GB · SHA-256 8f40ceffd444…93b1 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q3_K_L.gguf
gguf · 15,5 GB · SHA-256 010e34304a3c…24a9 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q3_K_M.gguf
gguf · 14,2 GB · SHA-256 6044cb24f76f…50c6 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q3_K_S.gguf
gguf · 12,8 GB · SHA-256 f801a5b0433f…b06e · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q4_0.gguf
gguf · 16,5 GB · SHA-256 7d1cea4d75bf…e718 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q4_1.gguf
gguf · 18,1 GB · SHA-256 70dc143be894…4d60 · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q4_K_M.gguf
gguf · 17,4 GB · SHA-256 bfadbafe4613…301c · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.i1-Q4_K_S.gguf
gguf · 16,5 GB · SHA-256 4cdb5c8c715b…5ecb · Hugging Face
Herunterladengemma-4-31B-it-qat-q4_0-unquantized.imatrix.gguf
gguf · 13,1 MB · SHA-256 af795f724a08…36a2 · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: google/gemma-4-31B-it-qat-q4_0-unquantized language: - en library_name: transformers license: apache-2.0 license_link: https://ai.google.dev/gemma/docs/gemma_4_license mradermacher: readme_rev: 1 quantized_by: mradermacher --- ## 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 IQ4_XS Q2_K_S IQ1_M Q3_K_S IQ2_XXS Q3_K_L IQ2_XS IQ2_S IQ1_S Q4_0 IQ3_XS Q4_1 IQ3_S --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: 1 --> weighted/imatrix quants of https://huggingface.co/google/gemma-4-31B-it-qat-q4_0-unquantized <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#gemma-4-31B-it-qat-q4_0-unquantized-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-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-it-qat-q4_0-unquantized-i1-GGUF/resolve/main/gemma-4-31B-it-qat-q4_0-unquantized.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-i1-GGUF/resolve/main/gemma-4-31B-it-qat-q4_0-unquantized.i1-IQ1_S.gguf) | i1-IQ1_S | 7.3 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-i1-GGUF/resolve/main/gemma-4-31B-it-qat-q4_0-unquantized.i1-IQ1_M.gguf) | i1-IQ1_M | 7.8 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-i1-GGUF/resolve/main/gemma-4-31B-it-qat-q4_0-unquantized.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 8.8 | | | [GGUF](https://hugging...
Source context: 1835 downloads · 4 likes · Library transformers · Repo mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-i1-GGUF
Source context: 900 downloads · 4 likes · Library transformers · Repo mradermacher/gemma-4-31B-it-qat-q4_0-unquantized-i1-GGUF
