LFM2 24B A2B Heretic Ara I1 GGUF
lfm1.0
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 53,5 MB–18,2 GB
- Modelo base
- trohrbaugh/LFM2-24B-A2B-heretic-ara
- Versão
- vRevision 9137798
- Atualizado
- 7 de out. de 2026
- Publicador
- @mradermacher
- Downloads
- 234
- Fonte
- Hugging Face
Descrição da fonte
About
weighted/imatrix quants of https://huggingface.co/trohrbaugh/LFM2-24B-A2B-heretic-ara
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/LFM2-24B-A2B-heretic-ara-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 | 0.2 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 4.9 | for the desperate |
| GGUF | i1-IQ1_M | 5.5 | mostly desperate |
| GGUF | i1-IQ2_XXS | 6.4 | |
| GGUF | i1-IQ2_XS | 7.1 | |
| GGUF | i1-IQ2_S | 7.2 | |
| GGUF | i1-IQ2_M | 7.9 | |
| GGUF | i1-Q2_K_S | 8.2 | very low quality |
| GGUF | i1-Q2_K | 8.8 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 9.3 | lower quality |
| GGUF | i1-IQ3_XS | 9.9 | |
| GGUF | i1-IQ3_S | 10.4 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 10.4 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 10.5 | |
| GGUF | i1-Q3_K_M | 11.5 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 12.4 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 12.8 | |
| GGUF | i1-Q4_0 | 13.6 | fast, low quality |
| GGUF | i1-Q4_K_S | 13.6 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 14.5 | fast, recommended |
| GGUF | i1-Q4_1 | 15.0 | |
| GGUF | i1-Q5_K_S | 16.5 | |
| GGUF | i1-Q5_K_M | 17.0 | |
| GGUF | i1-Q6_K | 19.7 | 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.
Fontes
1 fonte
Fontes
1 fonteVerificado 25 de ago.
Artefatos de modelo
24 artefatos
Artefatos de modelo
24 artefatosLFM2-24B-A2B-heretic-ara.i1-IQ1_M.gguf
gguf · 5,01 GB · SHA-256 d57438bb21c2…6897 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ1_S.gguf
gguf · 4,51 GB · SHA-256 b7cb5420c9cc…e2a2 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ2_M.gguf
gguf · 7,25 GB · SHA-256 82d4a30dbaa7…5144 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ2_S.gguf
gguf · 6,58 GB · SHA-256 1db5e18a4291…50d0 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ2_XS.gguf
gguf · 6,52 GB · SHA-256 368d340ec948…1f5e · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ2_XXS.gguf
gguf · 5,85 GB · SHA-256 74e502b04dc2…f7aa · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ3_M.gguf
gguf · 9,70 GB · SHA-256 513e480c4d3c…4ae1 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ3_S.gguf
gguf · 9,61 GB · SHA-256 56b742b4b0c8…0e2f · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ3_XS.gguf
gguf · 9,08 GB · SHA-256 ebaffb002008…7e12 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ3_XXS.gguf
gguf · 8,56 GB · SHA-256 1043505733ef…ef00 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-IQ4_XS.gguf
gguf · 11,9 GB · SHA-256 339693e4210a…2625 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q2_K_S.gguf
gguf · 7,51 GB · SHA-256 85698c528e75…1728 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q2_K.gguf
gguf · 8,10 GB · SHA-256 90acb0a27f5c…4f95 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q3_K_L.gguf
gguf · 11,5 GB · SHA-256 c479338c82e9…ea56 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q3_K_M.gguf
gguf · 10,6 GB · SHA-256 00543ddf6c1b…c414 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q3_K_S.gguf
gguf · 9,61 GB · SHA-256 1eb46697e288…b7a9 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q4_0.gguf
gguf · 12,6 GB · SHA-256 2e12d93518b7…4433 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q4_1.gguf
gguf · 13,9 GB · SHA-256 ee6ea14b6132…1193 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q4_K_M.gguf
gguf · 13,4 GB · SHA-256 782dfbf1595c…ef65 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q4_K_S.gguf
gguf · 12,6 GB · SHA-256 8a0b84653274…9df3 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q5_K_M.gguf
gguf · 15,8 GB · SHA-256 0f3be2109380…e8f4 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q5_K_S.gguf
gguf · 15,3 GB · SHA-256 878405440980…f9a0 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.i1-Q6_K.gguf
gguf · 18,2 GB · SHA-256 85223856206d…ad32 · Hugging Face
BaixarLFM2-24B-A2B-heretic-ara.imatrix.gguf
gguf · 53,5 MB · SHA-256 ff473a28082c…1905 · Hugging Face
BaixarTrechos de fonte
3 trechos
Trechos de fonte
3 trechos--- base_model: trohrbaugh/LFM2-24B-A2B-heretic-ara language: - en - ar - zh - fr - de - ja - ko - es - pt library_name: transformers license: other license_link: LICENSE license_name: lfm1.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - liquid - lfm2 - edge - heretic - uncensored - decensored - abliterated - ara --- ## 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/trohrbaugh/LFM2-24B-A2B-heretic-ara <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2-24B-A2B-heretic-ara-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/LFM2-24B-A2B-heretic-ara-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/LFM2-24B-A2B-heretic-ara-i1-GGUF/resolve/main/LFM2-24B-A2B-heretic-ara.imatrix.gguf) | imatrix | 0.2 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/LFM2-24B-A2B-heretic-ara-i1-GGUF/resolve/main/LFM2-24B-A2B-heretic-ara.i1-IQ1_S.gguf) | i1-IQ1_S | 4.9 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/LFM2-24B-A2B-heretic-ara-i1-GGUF/resolve/main/LFM2-24B-A2B-heretic-ara.i1-IQ1_M.gguf) | i1-IQ1_M | 5.5 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/LFM2-24B-A2B-heretic-ara-i1-GGUF/resolve/main/LFM2-24B-A2B-heretic-ara.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 6.4 | | | [GGUF](https://huggingface.co/mradermacher/LFM2-24B-A2B-heretic-ara-i1-GGUF/resolve/main/LFM2-24B-A2B-heretic-ara.i1-IQ2_XS.gguf) | i1-IQ2_XS | 7.1 | | | [GGUF](https://huggingface.co/mradermache...
Source context: 234 downloads · 1 likes · Library transformers · Repo mradermacher/LFM2-24B-A2B-heretic-ara-i1-GGUF
Source context: 196 downloads · 0 likes · Library transformers · Repo mradermacher/LFM2-24B-A2B-heretic-ara-i1-GGUF
