Tem um workflow do ComfyUI? Gere uma documentação legível direto no navegador.Torne um workflow legível.Experimentar agora ↗
For a convenient overview and download list, visit our model page for this model.
Fonte do modelo
Descrição da fonte
weighted/imatrix quants of https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Base
For a convenient overview and download list, visit our model page for this model.
static quants are available at
Fontes
1 fonteVerificado 5 de ago.
Artefatos de modelo
25 artefatosTrechos de fonte
3 trechosIf 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)
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.1 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 4.0 | for the desperate |
| GGUF | i1-IQ1_M | 4.2 | mostly desperate |
| GGUF | i1-IQ2_XXS | 4.5 | |
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
See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized.
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.
Mellum2-12B-A2.5B-Base.i1-IQ2_XS.gguf
gguf · 4,33 GB · SHA-256 d6762c96e21b…7f9f · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-IQ2_XXS.gguf
gguf · 4,10 GB · SHA-256 a57f09c97eed…1db1 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-IQ3_XS.gguf
gguf · 5,17 GB · SHA-256 c3397141d41c…c2d4 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-IQ3_XXS.gguf
gguf · 5,04 GB · SHA-256 bda25a4ab6d1…3dc5 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-IQ4_NL.gguf
gguf · 6,44 GB · SHA-256 d4f956ab98d1…c934 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-IQ4_XS.gguf
gguf · 6,20 GB · SHA-256 7d34c9ceec21…a845 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q2_K_S.gguf
gguf · 4,70 GB · SHA-256 a8db58929529…add4 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q3_K_L.gguf
gguf · 6,14 GB · SHA-256 30e45adb192c…6372 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q3_K_M.gguf
gguf · 5,90 GB · SHA-256 45516cf0b459…1b3a · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q3_K_S.gguf
gguf · 5,42 GB · SHA-256 140bf03dffa2…44f4 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q4_K_M.gguf
gguf · 7,52 GB · SHA-256 96bad3fdd663…5fab · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q4_K_S.gguf
gguf · 6,89 GB · SHA-256 fb2086b0fd28…237b · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q5_K_M.gguf
gguf · 8,58 GB · SHA-256 09de5299f345…2370 · Hugging Face
BaixarMellum2-12B-A2.5B-Base.i1-Q5_K_S.gguf
gguf · 8,04 GB · SHA-256 d417cbbbf7ba…2549 · Hugging Face
Baixar--- base_model: JetBrains/Mellum2-12B-A2.5B-Base language: - en library_name: transformers license: apache-2.0 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 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: --> weighted/imatrix quants of https://huggingface.co/JetBrains/Mellum2-12B-A2.5B-Base <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Mellum2-12B-A2.5B-Base-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/Mellum2-12B-A2.5B-Base-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/Mellum2-12B-A2.5B-Base-i1-GGUF/resolve/main/Mellum2-12B-A2.5B-Base.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF/resolve/main/Mellum2-12B-A2.5B-Base.i1-IQ1_S.gguf) | i1-IQ1_S | 4.0 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF/resolve/main/Mellum2-12B-A2.5B-Base.i1-IQ1_M.gguf) | i1-IQ1_M | 4.2 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF/resolve/main/Mellum2-12B-A2.5B-Base.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.5 | | | [GGUF](https://huggingface.co/mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF/resolve/main/Mellum2-12B-A2.5B-Base.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | | | [GGUF](https://huggingface.co/mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF/resolve/main/Mellum2-12B-A2.5B-Base.i1-IQ2_S.gguf) | i1-IQ2_S | 4.8 | | | [GGUF](https://huggingface.co/mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF/resolve/main...
Source context: 896 downloads · 0 likes · Library transformers · Repo mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF
Source context: 728 downloads · 0 likes · Library transformers · Repo mradermacher/Mellum2-12B-A2.5B-Base-i1-GGUF
| i1-IQ2_XS |
| 4.8 |
| GGUF | i1-IQ2_S | 4.8 |
| GGUF | i1-IQ2_M | 5.1 |
| GGUF | i1-Q2_K | 5.1 | IQ3_XXS probably better |
| GGUF | i1-Q2_K_S | 5.1 | very low quality |
| GGUF | i1-IQ3_XXS | 5.5 | lower quality |
| GGUF | i1-IQ3_XS | 5.6 |
| GGUF | i1-Q3_K_S | 5.9 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 5.9 | beats Q3_K* |
| GGUF | i1-IQ3_M | 6.0 |
| GGUF | i1-Q3_K_M | 6.4 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 6.7 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 6.8 |
| GGUF | i1-IQ4_NL | 7.0 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 7.0 | fast, low quality |
| GGUF | i1-Q4_K_S | 7.5 | optimal size/speed/quality |
| GGUF | i1-Q4_1 | 7.8 |
| GGUF | i1-Q4_K_M | 8.2 | fast, recommended |
| GGUF | i1-Q5_K_S | 8.7 |
| GGUF | i1-Q5_K_M | 9.3 |
| GGUF | i1-Q6_K | 11.0 | practically like static Q6_K |
