LFM2 12B A1B SpeedDemon High Intelligence Series B I1 GGUF
For a convenient overview and download list, visit our model page for this model.
Source du modèle
- Type
- Other
- Taille du fichier
- 22,5 MB–8,63 GB
- Modèle de base
- DavidAU/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B
- Version
- vRevision 08f4fcd
- Mis à jour
- 1 oct. 2026
- Éditeur
- @mradermacher
- Téléchargements
- 1,4 k
- Source
- Hugging Face
Description de la source
About
weighted/imatrix quants of https://huggingface.co/DavidAU/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B
For a convenient overview and download list, visit our model page for this model.
static quants are available at https://huggingface.co/mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-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 | 0.1 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 2.4 | for the desperate |
| GGUF | i1-IQ1_M | 2.7 | mostly desperate |
| GGUF | i1-IQ2_XXS | 3.1 | |
| GGUF | i1-IQ2_XS | 3.4 | |
| GGUF | i1-IQ2_S | 3.5 | |
| GGUF | i1-IQ2_M | 3.8 | |
| GGUF | i1-Q2_K_S | 3.9 | very low quality |
| GGUF | i1-Q2_K | 4.2 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 4.5 | lower quality |
| GGUF | i1-IQ3_XS | 4.7 | |
| GGUF | i1-IQ3_S | 5.0 | beats Q3_K* |
| GGUF | i1-Q3_K_S | 5.0 | IQ3_XS probably better |
| GGUF | i1-IQ3_M | 5.1 | |
| GGUF | i1-Q3_K_M | 5.5 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 5.9 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 6.1 | |
| GGUF | i1-IQ4_NL | 6.5 | prefer IQ4_XS |
| GGUF | i1-Q4_0 | 6.5 | fast, low quality |
| GGUF | i1-Q4_K_S | 6.5 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 6.9 | fast, recommended |
| GGUF | i1-Q4_1 | 7.2 | |
| GGUF | i1-Q5_K_S | 7.9 | |
| GGUF | i1-Q5_K_M | 8.1 | |
| GGUF | i1-Q6_K | 9.4 | 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.
Sources
1 source
Sources
1 sourceVérifié 1 oct.
Artefacts du modèle
25 artefacts
Artefacts du modèle
25 artefactsLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ1_M.gguf
gguf · 2,40 GB · SHA-256 f86c60cdc291…5fb8 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ1_S.gguf
gguf · 2,16 GB · SHA-256 dd9df026c085…acdf · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ2_M.gguf
gguf · 3,45 GB · SHA-256 2bb91c874461…ec20 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ2_S.gguf
gguf · 3,14 GB · SHA-256 5df1a0f601ed…b360 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ2_XS.gguf
gguf · 3,11 GB · SHA-256 bb126038fd67…b788 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ2_XXS.gguf
gguf · 2,79 GB · SHA-256 0d1165e61d67…f0e4 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ3_M.gguf
gguf · 4,61 GB · SHA-256 41cb961c8848…3382 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ3_S.gguf
gguf · 4,57 GB · SHA-256 33f3d885d78e…cd0e · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ3_XS.gguf
gguf · 4,32 GB · SHA-256 4d594490d8f5…06db · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ3_XXS.gguf
gguf · 4,07 GB · SHA-256 f98cbfd398c4…2a6d · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ4_NL.gguf
gguf · 5,95 GB · SHA-256 0c89ba119c09…3adf · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ4_XS.gguf
gguf · 5,63 GB · SHA-256 e888675b30cd…3bbc · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q2_K_S.gguf
gguf · 3,58 GB · SHA-256 b23b676d6b1f…3107 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q2_K.gguf
gguf · 3,86 GB · SHA-256 b81b592a5559…7404 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q3_K_L.gguf
gguf · 5,44 GB · SHA-256 e289e1d18679…c67a · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q3_K_M.gguf
gguf · 5,02 GB · SHA-256 12c7ed290636…3dfb · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q3_K_S.gguf
gguf · 4,57 GB · SHA-256 15b673fd4d0c…8ceb · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q4_0.gguf
gguf · 5,97 GB · SHA-256 fab90eca5cd8…f69a · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q4_1.gguf
gguf · 6,60 GB · SHA-256 f1a74747b852…4267 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q4_K_M.gguf
gguf · 6,35 GB · SHA-256 ccdcb2642766…af7c · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q4_K_S.gguf
gguf · 5,98 GB · SHA-256 813696c8e26e…6aa2 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q5_K_M.gguf
gguf · 7,46 GB · SHA-256 caf3c7035455…e1ae · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q5_K_S.gguf
gguf · 7,25 GB · SHA-256 b28dc081761b…0de9 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-Q6_K.gguf
gguf · 8,63 GB · SHA-256 014633a36836…34b1 · Hugging Face
TéléchargerLFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.imatrix.gguf
gguf · 22,5 MB · SHA-256 f5801d475899…f6d9 · Hugging Face
TéléchargerExtraits de sources
3 extraits
Extraits de sources
3 extraits--- base_model: DavidAU/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B language: - en library_name: transformers license: apache-2.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - finetune - unsloth - mixture of experts - sparse moe - moe --- ## 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/DavidAU/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-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/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-GGUF/resolve/main/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-GGUF/resolve/main/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.4 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-GGUF/resolve/main/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.7 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-GGUF/resolve/main/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B.i1-IQ2_XXS.gguf) | i1-IQ2_X...
Source context: 1415 downloads · 2 likes · Library transformers · Repo mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-GGUF
Source context: 370 downloads · 2 likes · Library transformers · Repo mradermacher/LFM2-12B-A1B-SpeedDemon-High-Intelligence-Series-B-i1-GGUF
