Zum Inhalt springen
ModelÜberprüftExtern
Herunterladen

LFM2.5 8B A1B Coder I1 GGUF

For a convenient overview and download list, visit our model page for this model.

Quellehuggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/tree/a414a108ba674ed70ff732a59d7d6f15f62984de
ArtOtherBasismodelljosephmayo/LFM2.5-8B-A1B-CoderVersionRevision a414a10Verleger@mradermacherCBewertung

Modellquelle

Art
Other
Dateigröße
16,6 MB–6,48 GB
Basismodell
josephmayo/LFM2.5-8B-A1B-Coder
Version
vRevision a414a10
Aktualisiert
3. Okt. 2026
Verleger
@mradermacher
Downloads
1403
Parameter
8B
Quelle
Hugging Face

Quellenbeschreibung

About

weighted/imatrix quants of https://huggingface.co/josephmayo/LFM2.5-8B-A1B-Coder

For a convenient overview and download list, visit our model page for this model.

static quants are available at https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-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)

LinkTypeSize/GBNotes
GGUFimatrix0.1imatrix file (for creating your own quants)
GGUFi1-IQ1_S1.9for the desperate
GGUFi1-IQ1_M2.1mostly desperate
GGUFi1-IQ2_XXS2.4
GGUFi1-IQ2_XS2.7
GGUFi1-IQ2_S2.7
GGUFi1-IQ2_M2.9
GGUFi1-Q2_K_S3.1very low quality
GGUFi1-Q2_K3.3IQ3_XXS probably better
GGUFi1-IQ3_XXS3.4lower quality
GGUFi1-IQ3_XS3.7
GGUFi1-IQ3_S3.9beats Q3_K*
GGUFi1-Q3_K_S3.9IQ3_XS probably better
GGUFi1-IQ3_M3.9
GGUFi1-Q3_K_M4.2IQ3_S probably better
GGUFi1-Q3_K_L4.5IQ3_M probably better
GGUFi1-IQ4_XS4.7
GGUFi1-IQ4_NL4.9prefer IQ4_XS
GGUFi1-Q4_05.0fast, low quality
GGUFi1-Q4_K_S5.0optimal size/speed/quality
GGUFi1-Q4_K_M5.3fast, recommended
GGUFi1-Q4_15.5
GGUFi1-Q5_K_S6.0
GGUFi1-Q5_K_M6.1
GGUFi1-Q6_K7.1practically 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
Hugging FacePrimärVersion a414a108ba674ed70ff732a59d7d6f15f62984de
huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/tree/a414a108ba674ed70ff732a59d7d6f15f62984de

Verifiziert 3. Okt.

Modellartefakte

25 Artefakte

LFM2.5-8B-A1B-Coder.i1-IQ1_M.gguf

gguf · 1,87 GB · SHA-256 56b4a5e44e68…ce29 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ1_S.gguf

gguf · 1,70 GB · SHA-256 b5a0cbe0012a…9abf · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ2_M.gguf

gguf · 2,65 GB · SHA-256 3f570d83902c…8def · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ2_S.gguf

gguf · 2,41 GB · SHA-256 1cd3e82f641c…c489 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ2_XS.gguf

gguf · 2,40 GB · SHA-256 3c0d23143911…2529 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ2_XXS.gguf

gguf · 2,16 GB · SHA-256 41f2f3267501…3354 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ3_M.gguf

gguf · 3,52 GB · SHA-256 a13bccc508db…c881 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ3_S.gguf

gguf · 3,50 GB · SHA-256 f9ee097925b7…a244 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ3_XS.gguf

gguf · 3,31 GB · SHA-256 da4e699c8704…00bb · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ3_XXS.gguf

gguf · 3,11 GB · SHA-256 bc8952c66030…8605 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ4_NL.gguf

gguf · 4,51 GB · SHA-256 0fdbb31a40ac…9a49 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-IQ4_XS.gguf

gguf · 4,27 GB · SHA-256 b0abd5328a9f…70e6 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q2_K_S.gguf

gguf · 2,75 GB · SHA-256 9454caeadbcc…c23a · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q2_K.gguf

gguf · 2,97 GB · SHA-256 c4a3cceed47d…259f · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q3_K_L.gguf

gguf · 4,13 GB · SHA-256 4db09ed16f42…2f7f · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q3_K_M.gguf

gguf · 3,83 GB · SHA-256 90c49d6c028e…ba03 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q3_K_S.gguf

gguf · 3,50 GB · SHA-256 5926ec8864bc…a38b · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q4_0.gguf

gguf · 4,52 GB · SHA-256 a21750cb2126…be93 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q4_1.gguf

gguf · 4,99 GB · SHA-256 ca51da491b10…f773 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q4_K_M.gguf

gguf · 4,80 GB · SHA-256 ef576392c3d9…56c0 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q4_K_S.gguf

gguf · 4,53 GB · SHA-256 e3ec4c844e73…588d · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q5_K_M.gguf

gguf · 5,62 GB · SHA-256 d5cdbceed05c…f132 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q5_K_S.gguf

gguf · 5,47 GB · SHA-256 99fee5042de2…13df · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.i1-Q6_K.gguf

gguf · 6,48 GB · SHA-256 8e309605a486…b6d3 · Hugging Face

Herunterladen

LFM2.5-8B-A1B-Coder.imatrix.gguf

gguf · 16,6 MB · SHA-256 a34c88daced3…a370 · Hugging Face

Herunterladen

Quellenauszüge

3 Auszüge
Readme11. Julihuggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF

--- base_model: josephmayo/LFM2.5-8B-A1B-Coder language: - en library_name: transformers mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - transformers - code - real-world-coding - multilingual - lfm2_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/josephmayo/LFM2.5-8B-A1B-Coder <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#LFM2.5-8B-A1B-Coder-i1-GGUF).*** static quants are available at https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-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/LFM2.5-8B-A1B-Coder-i1-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) | | [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.i1-IQ1_S.gguf) | i1-IQ1_S | 1.9 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.i1-IQ1_M.gguf) | i1-IQ1_M | 2.1 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.4 | | | [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | | [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/resolve/main/LFM2.5-8B-A1B-Coder.i1-IQ2_S.gguf) | i1-IQ2_S | 2.7 | | | [GGUF](https://huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF/resolve...

Note3. Okt.huggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF

Source context: 1403 downloads · 4 likes · Library transformers · Repo mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF

Note17. Julihuggingface.co/mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF

Source context: 1337 downloads · 1 likes · Library transformers · Repo mradermacher/LFM2.5-8B-A1B-Coder-i1-GGUF