mradermacher's picture
auto-patch README.md
22c3c15 verified
---
base_model: ai21labs/AI21-Jamba-Large-1.5
language:
- en
- fr
- de
- nl
- es
- pt
- it
- ar
- he
library_name: transformers
license: other
license_link: https://www.ai21.com/licenses/jamba-open-model-license
license_name: jamba-open-model-license
mradermacher:
readme_rev: 1
quantized_by: mradermacher
tags:
- mamba
- jamba
- moe
---
## About
<!-- ### quantize_version: 2 -->
<!-- ### output_tensor_quantised: 1 -->
<!-- ### convert_type: hf -->
<!-- ### vocab_type: -->
<!-- ### tags: -->
static quants of https://huggingface.co/ai21labs/AI21-Jamba-Large-1.5
<!-- provided-files -->
***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#AI21-Jamba-Large-1.5-GGUF).***
weighted/imatrix quants are available at https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-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 |
|:-----|:-----|--------:|:------|
| [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q2_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q2_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q2_K.gguf.part3of3) | Q2_K | 143.8 | |
| [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_S.gguf.part4of4) | Q3_K_S | 171.7 | |
| [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_M.gguf.part4of4) | Q3_K_M | 189.0 | lower quality |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_L.gguf.part1of5) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_L.gguf.part2of5) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_L.gguf.part3of5) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_L.gguf.part4of5) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q3_K_L.gguf.part5of5) | Q3_K_L | 203.6 | |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.IQ4_XS.gguf.part1of5) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.IQ4_XS.gguf.part2of5) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.IQ4_XS.gguf.part3of5) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.IQ4_XS.gguf.part4of5) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.IQ4_XS.gguf.part5of5) | IQ4_XS | 214.3 | |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_S.gguf.part5of5) | Q4_K_S | 226.3 | fast, recommended |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q4_K_M.gguf.part5of5) | Q4_K_M | 240.4 | fast, recommended |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_S.gguf.part1of6) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_S.gguf.part2of6) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_S.gguf.part3of6) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_S.gguf.part4of6) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_S.gguf.part5of6) [P6](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_S.gguf.part6of6) | Q5_K_S | 274.3 | |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_M.gguf.part1of6) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_M.gguf.part2of6) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_M.gguf.part3of6) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_M.gguf.part4of6) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_M.gguf.part5of6) [P6](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q5_K_M.gguf.part6of6) | Q5_K_M | 282.5 | |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q6_K.gguf.part1of7) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q6_K.gguf.part2of7) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q6_K.gguf.part3of7) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q6_K.gguf.part4of7) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q6_K.gguf.part5of7) [P6](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q6_K.gguf.part6of7) [P7](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q6_K.gguf.part7of7) | Q6_K | 327.1 | very good quality |
| [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part1of9) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part2of9) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part3of9) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part4of9) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part5of9) [P6](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part6of9) [P7](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part7of9) [P8](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part8of9) [P9](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-GGUF/resolve/main/AI21-Jamba-Large-1.5.Q8_0.gguf.part9of9) | Q8_0 | 423.7 | fast, best quality |
Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):
![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.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](https://www.nethype.de/), for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/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.
<!-- end -->