Ichigo Llama3.1 S Instruct v0.4 I1 GGUF
static quants are available at
Source du modèle
- Type
- Other
- Taille du fichier
- 1,88–6,15 GB
- Modèle de base
- Menlo/Ichigo-llama3.1-s-instruct-v0.4
- Version
- vRevision a4f5913
- Mis à jour
- 31 oct. 2026
- Téléchargements
- 583
- Source
- Hugging Face
Description de la source
About
weighted/imatrix quants of https://huggingface.co/Menlo/Ichigo-llama3.1-s-instruct-v0.4
static quants are available at https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-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 | i1-IQ1_S | 2.1 | for the desperate |
| GGUF | i1-IQ1_M | 2.3 | mostly desperate |
| GGUF | i1-IQ2_XXS | 2.5 | |
| GGUF | i1-IQ2_XS | 2.7 | |
| GGUF | i1-IQ2_S | 2.9 | |
| GGUF | i1-IQ2_M | 3.1 | |
| GGUF | i1-Q2_K | 3.3 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 3.4 | lower quality |
| GGUF | i1-IQ3_XS | 3.6 | |
| GGUF | i1-Q3_K_S | 3.8 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 3.8 | beats Q3_K* |
| GGUF | i1-IQ3_M | 3.9 | |
| GGUF | i1-Q3_K_M | 4.1 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 4.4 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 4.6 | |
| GGUF | i1-Q4_0_4_4 | 4.8 | fast on arm, low quality |
| GGUF | i1-Q4_0_4_8 | 4.8 | fast on arm+i8mm, low quality |
| GGUF | i1-Q4_0_8_8 | 4.8 | fast on arm+sve, low quality |
| GGUF | i1-Q4_0 | 4.8 | fast, low quality |
| GGUF | i1-Q4_K_S | 4.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 5.0 | fast, recommended |
| GGUF | i1-Q5_K_S | 5.7 | |
| GGUF | i1-Q5_K_M | 5.8 | |
| GGUF | i1-Q6_K | 6.7 | 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.
Sources
1 source
Sources
1 sourceVérifié 31 oct.
Download files
Repository files
File inventory only; completeness is unverified.
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ1_M.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ1_S.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_M.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_S.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_XS.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_XXS.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ3_M.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ3_S.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ3_XS.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ3_XXS.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-IQ4_XS.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q2_K.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q3_K_L.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q3_K_M.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q3_K_S.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q4_0.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q4_0_4_4.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q4_0_4_8.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q4_0_8_8.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q4_K_M.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q4_K_S.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q5_K_M.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q5_K_S.gguf
- Ichigo-llama3.1-s-instruct-v0.4.i1-Q6_K.gguf
Artefacts du modèle
24 artefacts
Artefacts du modèle
24 artefactsIchigo-llama3.1-s-instruct-v0.4.i1-IQ1_M.gguf
gguf · 2,02 GB · SHA-256 2d63b7fa00a2…7f80 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ1_S.gguf
gguf · 1,88 GB · SHA-256 49f7f1dee62e…c075 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ2_M.gguf
gguf · 2,75 GB · SHA-256 ae8d63f33e65…db0e · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ2_S.gguf
gguf · 2,57 GB · SHA-256 5bcd65b5e074…ada0 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ2_XS.gguf
gguf · 2,43 GB · SHA-256 a00fae71949e…b3c2 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ2_XXS.gguf
gguf · 2,24 GB · SHA-256 3ac37bf4781a…71c4 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ3_M.gguf
gguf · 3,53 GB · SHA-256 07907619db85…8ff8 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ3_S.gguf
gguf · 3,43 GB · SHA-256 26a73af8ec17…87e4 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ3_XS.gguf
gguf · 3,28 GB · SHA-256 38940d75f722…4962 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ3_XXS.gguf
gguf · 3,05 GB · SHA-256 56e993f20911…153a · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-IQ4_XS.gguf
gguf · 4,14 GB · SHA-256 b690bfd66adb…16ac · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q2_K.gguf
gguf · Q2_K (unverified) · 2,96 GB · SHA-256 8d6c39410410…dbcf · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q3_K_L.gguf
gguf · Q3_K_L (unverified) · 4,03 GB · SHA-256 2b2cb0a04751…6d9f · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q3_K_M.gguf
gguf · Q3_K_M (unverified) · 3,75 GB · SHA-256 98e4917c0b30…8123 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q3_K_S.gguf
gguf · Q3_K_S (unverified) · 3,42 GB · SHA-256 1c7ffc25904f…f721 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q4_0_4_4.gguf
gguf · Q4_0_4_4 (unverified) · 4,34 GB · SHA-256 4f5104a2c7a5…32bf · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q4_0_4_8.gguf
gguf · Q4_0_4_8 (unverified) · 4,34 GB · SHA-256 7086d07be79d…1659 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q4_0_8_8.gguf
gguf · Q4_0_8_8 (unverified) · 4,34 GB · SHA-256 1ecc8c5d76a5…0d4a · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q4_0.gguf
gguf · Q4_0 (unverified) · 4,36 GB · SHA-256 f00ab32397b1…c942 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q4_K_M.gguf
gguf · Q4_K_M (unverified) · 4,59 GB · SHA-256 979980add8f0…7fc7 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q4_K_S.gguf
gguf · Q4_K_S (unverified) · 4,37 GB · SHA-256 c6201b555eb3…01d4 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q5_K_M.gguf
gguf · Q5_K_M (unverified) · 5,34 GB · SHA-256 e6e7011ceee8…498f · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q5_K_S.gguf
gguf · Q5_K_S (unverified) · 5,22 GB · SHA-256 d6fdab21a11c…a099 · Hugging Face
Download fileIchigo-llama3.1-s-instruct-v0.4.i1-Q6_K.gguf
gguf · Q6_K (unverified) · 6,15 GB · SHA-256 ca3531103993…6b52 · Hugging Face
Download fileExtraits de sources
3 extraits
Extraits de sources
3 extraits--- base_model: Menlo/Ichigo-llama3.1-s-instruct-v0.4 datasets: - homebrewltd/instruction-speech-whispervq-v2 language: - en library_name: transformers license: apache-2.0 quantized_by: mradermacher tags: - sound language model - audio-text-to-text - torchtune --- ## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hf --> <!-- ### vocab_type: --> <!-- ### tags: nicoboss --> weighted/imatrix quants of https://huggingface.co/Menlo/Ichigo-llama3.1-s-instruct-v0.4 <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-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/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llama3.1-s-instruct-v0.4.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llama3.1-s-instruct-v0.4.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | mostly desperate | | [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | | [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | | [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | | [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llama3.1-s-instruct-v0.4.i1-IQ2_M.gguf) | i1-IQ2_M | 3.1 | | | [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llama3.1-s-instruct-v0.4.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF/resolve/main/Ichigo-llam...
Source context: 583 downloads · 4 likes · Pipeline audio-text-to-text · Library transformers · Repo mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF
Source context: 455 downloads · 4 likes · Pipeline audio-text-to-text · Library transformers · Repo mradermacher/Ichigo-llama3.1-s-instruct-v0.4-i1-GGUF
