Atlas Trm10 Gemma4 26b I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Modellquelle
- Art
- Other
- Dateigröße
- 54,3 MB–21,1 GB
- Basismodell
- senaro/atlas-trm10-gemma4-26b
- Version
- vRevision d999842
- Aktualisiert
- 3. Okt. 2026
- Verleger
- @mradermacher
- Downloads
- 2209
- Parameter
- 26B
- Aufgaben
- Textgenerierung
- Quelle
- Hugging Face
Quellenbeschreibung
About
weighted/imatrix quants of https://huggingface.co/senaro/atlas-trm10-gemma4-26b
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-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 | 0.2 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 8.4 | for the desperate |
| GGUF | i1-IQ1_M | 8.8 | mostly desperate |
| GGUF | i1-IQ2_XXS | 9.4 | |
| GGUF | i1-IQ2_XS | 9.9 | |
| GGUF | i1-IQ2_S | 10.0 | |
| GGUF | i1-IQ2_M | 10.5 | |
| GGUF | i1-Q2_K | 10.7 | IQ3_XXS probably better |
| GGUF | i1-Q2_K_S | 10.7 | very low quality |
| GGUF | i1-IQ3_XXS | 11.4 | lower quality |
| GGUF | i1-IQ3_XS | 11.7 | |
| GGUF | i1-IQ3_S | 12.3 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 12.3 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 12.5 | |
| GGUF | i1-Q3_K_M | 13.4 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 13.9 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 14.0 | |
| GGUF | i1-Q4_0 | 14.6 | fast, low quality |
| GGUF | i1-Q4_K_S | 15.6 | optimal size/speed/quality |
| GGUF | i1-Q4_1 | 16.1 | |
| GGUF | i1-Q4_K_M | 16.9 | fast, recommended |
| GGUF | i1-Q5_K_S | 18.1 | |
| GGUF | i1-Q5_K_M | 19.2 | |
| GGUF | i1-Q6_K | 22.7 | 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 Artefakteatlas-trm10-gemma4-26b.i1-IQ1_M.gguf
gguf · 8,07 GB · SHA-256 18484d2c8624…633f · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ1_S.gguf
gguf · 7,72 GB · SHA-256 cd5fd63d6595…1210 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ2_M.gguf
gguf · 9,66 GB · SHA-256 3bf05e64cbe0…52ca · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ2_S.gguf
gguf · 9,20 GB · SHA-256 72d4c391b74d…4e14 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ2_XS.gguf
gguf · 9,14 GB · SHA-256 697c31ba632d…4c19 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ2_XXS.gguf
gguf · 8,66 GB · SHA-256 87c8f6d94d6a…4234 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ3_M.gguf
gguf · 11,5 GB · SHA-256 1c5aee914f95…594c · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ3_S.gguf
gguf · 11,4 GB · SHA-256 727f56b87d16…4ed2 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ3_XS.gguf
gguf · 10,8 GB · SHA-256 e55294b28817…fa48 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ3_XXS.gguf
gguf · 10,5 GB · SHA-256 569061b8cd8c…d23b · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-IQ4_XS.gguf
gguf · 13,0 GB · SHA-256 71e8f2ac870d…4b67 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q2_K_S.gguf
gguf · 9,89 GB · SHA-256 6498b6d24b13…ef8f · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q2_K.gguf
gguf · 9,86 GB · SHA-256 be713526af15…54e2 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q3_K_L.gguf
gguf · 12,9 GB · SHA-256 c4149cac24a0…d8e0 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q3_K_M.gguf
gguf · 12,4 GB · SHA-256 532cb25a395f…fdce · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q3_K_S.gguf
gguf · 11,4 GB · SHA-256 21649e9ac7c2…717b · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q4_0.gguf
gguf · 13,5 GB · SHA-256 05e4119d1cac…cedb · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q4_1.gguf
gguf · 14,9 GB · SHA-256 868588db49b3…8792 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q4_K_M.gguf
gguf · 15,6 GB · SHA-256 7968bdd164e8…cfa1 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q4_K_S.gguf
gguf · 14,4 GB · SHA-256 5810299b45c6…da60 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q5_K_M.gguf
gguf · 17,8 GB · SHA-256 b155a3b6e3c6…7b71 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q5_K_S.gguf
gguf · 16,8 GB · SHA-256 93708a2dea91…7078 · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.i1-Q6_K.gguf
gguf · 21,1 GB · SHA-256 1694a606a7df…14bc · Hugging Face
Herunterladenatlas-trm10-gemma4-26b.imatrix.gguf
gguf · 54,3 MB · SHA-256 3dbeef3c9f00…801a · Hugging Face
HerunterladenQuellenauszüge
3 Auszüge
Quellenauszüge
3 Auszüge--- base_model: senaro/atlas-trm10-gemma4-26b language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - text-generation-inference - transformers - unsloth - gemma4 --- ## 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/senaro/atlas-trm10-gemma4-26b <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#atlas-trm10-gemma4-26b-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-GGUF **This is a vision model - mmproj files (if any) will be in the [static repository](https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-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/atlas-trm10-gemma4-26b-i1-GGUF/resolve/main/atlas-trm10-gemma4-26b.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-i1-GGUF/resolve/main/atlas-trm10-gemma4-26b.i1-IQ1_S.gguf) | i1-IQ1_S | 8.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-i1-GGUF/resolve/main/atlas-trm10-gemma4-26b.i1-IQ1_M.gguf) | i1-IQ1_M | 8.8 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-i1-GGUF/resolve/main/atlas-trm10-gemma4-26b.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 9.4 | | | [GGUF](https://huggingface.co/mradermacher/atlas-trm10-gemma4-26b-i1-GGUF/resolve/main/atlas-trm10-gemma4-26b.i1-IQ2_XS.gguf) | i1-IQ2_XS | 9.9 | | | [GGUF](https://hu...
Source context: 2209 downloads · 0 likes · Library transformers · Repo mradermacher/atlas-trm10-gemma4-26b-i1-GGUF
Source context: 3128 downloads · 0 likes · Library transformers · Repo mradermacher/atlas-trm10-gemma4-26b-i1-GGUF
