Skip to content
ModelVerifiedExternal
Browse files

Amethyst 12B v3 GGUF

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

Sourcehuggingface.co/mradermacher/Amethyst-12B-v3-GGUF/tree/edba598fe8dfa2a20499f66ef1efa6ca847fc26e
KindOtherBase modelLambent/Amethyst-12B-v3VersionRevision edba598Publisher@mradermacherCgrade

Model source

Kind
Other
File size
4.46–12.1 GB
Base model
Lambent/Amethyst-12B-v3
Version
vRevision edba598
Updated
Oct 3, 2026
Publisher
@mradermacher
Downloads
136
Parameters
12B
Source
Hugging Face

Source description

About

static quants of https://huggingface.co/Lambent/Amethyst-12B-v3

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

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Amethyst-12B-v3-i1-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
GGUFQ2_K4.9
GGUFQ3_K_S5.6
GGUFQ3_K_M6.2lower quality
GGUFQ3_K_L6.7
GGUFIQ4_XS6.9
GGUFQ4_K_S7.2fast, recommended
GGUFQ4_K_M7.6fast, recommended
GGUFQ5_K_S8.6
GGUFQ5_K_M8.8
GGUFQ6_K10.2very good quality
GGUFQ8_013.1fast, best quality

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.

Sources

1 source
Hugging FacePrimaryVersion edba598fe8dfa2a20499f66ef1efa6ca847fc26e
huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/tree/edba598fe8dfa2a20499f66ef1efa6ca847fc26e

Verified Oct 3

Download files

Model artifacts

11 artifacts

Amethyst-12B-v3.IQ4_XS.gguf

gguf · 6.33 GB · SHA-256 d509cc9717fa…8094 · Hugging Face

Download file

Amethyst-12B-v3.Q2_K.gguf

gguf · 4.46 GB · SHA-256 57384f94da63…6977 · Hugging Face

Download file

Amethyst-12B-v3.Q3_K_L.gguf

gguf · 6.11 GB · SHA-256 f83f86d3d07e…5d33 · Hugging Face

Download file

Amethyst-12B-v3.Q3_K_M.gguf

gguf · 5.67 GB · SHA-256 1d9f031b0cfa…3af2 · Hugging Face

Download file

Amethyst-12B-v3.Q3_K_S.gguf

gguf · 5.15 GB · SHA-256 8df7da7ec227…1389 · Hugging Face

Download file

Amethyst-12B-v3.Q4_K_M.gguf

gguf · 6.96 GB · SHA-256 ae9626e9f1e8…8acb · Hugging Face

Download file

Amethyst-12B-v3.Q4_K_S.gguf

gguf · 6.63 GB · SHA-256 585513ea76f4…b5be · Hugging Face

Download file

Amethyst-12B-v3.Q5_K_M.gguf

gguf · 8.13 GB · SHA-256 d3afc50e6757…08d7 · Hugging Face

Download file

Amethyst-12B-v3.Q5_K_S.gguf

gguf · 7.93 GB · SHA-256 9777bd54eecd…66f8 · Hugging Face

Download file

Amethyst-12B-v3.Q6_K.gguf

gguf · 9.37 GB · SHA-256 d6eaad27944e…b45c · Hugging Face

Download file

Amethyst-12B-v3.Q8_0.gguf

gguf · 12.1 GB · SHA-256 b0481718ba39…84f0 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/mradermacher/Amethyst-12B-v3-GGUF

--- base_model: Lambent/Amethyst-12B-v3 language: - en library_name: transformers license: cc-by-nc-4.0 mradermacher: readme_rev: 1 quantized_by: mradermacher tags: - not-for-all-audiences --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: --> <!-- ### quants: x-f16 Q4_K_S Q2_K Q8_0 Q6_K Q3_K_M Q3_K_S Q3_K_L Q4_K_M Q5_K_S Q5_K_M IQ4_XS --> <!-- ### quants_skip: --> <!-- ### skip_mmproj: --> static quants of https://huggingface.co/Lambent/Amethyst-12B-v3 <!-- provided-files --> ***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Amethyst-12B-v3-GGUF).*** weighted/imatrix quants are available at https://huggingface.co/mradermacher/Amethyst-12B-v3-i1-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/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.Q2_K.gguf) | Q2_K | 4.9 | | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.Q3_K_S.gguf) | Q3_K_S | 5.6 | | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.Q3_K_M.gguf) | Q3_K_M | 6.2 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.Q3_K_L.gguf) | Q3_K_L | 6.7 | | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.IQ4_XS.gguf) | IQ4_XS | 6.9 | | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.Q4_K_S.gguf) | Q4_K_S | 7.2 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.Q4_K_M.gguf) | Q4_K_M | 7.6 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B-v3.Q5_K_S.gguf) | Q5_K_S | 8.6 | | | [GGUF](https://huggingface.co/mradermacher/Amethyst-12B-v3-GGUF/resolve/main/Amethyst-12B...

NoteOct 3huggingface.co/mradermacher/Amethyst-12B-v3-GGUF

Source context: 136 downloads · 1 likes · Library transformers · Repo mradermacher/Amethyst-12B-v3-GGUF

NoteJul 17huggingface.co/mradermacher/Amethyst-12B-v3-GGUF

Source context: 47 downloads · 1 likes · Library transformers · Repo mradermacher/Amethyst-12B-v3-GGUF