Hugging Face's logo

mradermacher
/
AI21-Jamba-Large-1.5-i1-GGUF

Transformers
mamba
jamba
Mixture of Experts
Model card Files
xet
Community
mradermacher commited on
Commit
3b2e98a
·
verified ·
1 Parent(s): 7eade28

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -49,7 +49,9 @@ more details, including on how to concatenate multi-part files.
49
  | Link | Type | Size/GB | Notes |
50
  |:-----|:-----|--------:|:------|
51
  | [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q2_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q2_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q2_K.gguf.part3of3) | i1-Q2_K | 143.8 | IQ3_XXS probably better |
 
52
  | [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part4of4) | i1-IQ3_M | 173.6 | |
 
53
 
54
  Here is a handy graph by ikawrakow comparing some lower-quality quant
55
  types (lower is better):
 
49
  | Link | Type | Size/GB | Notes |
50
  |:-----|:-----|--------:|:------|
51
  | [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q2_K.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q2_K.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q2_K.gguf.part3of3) | i1-Q2_K | 143.8 | IQ3_XXS probably better |
52
+ | [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_XXS.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_XXS.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_XXS.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_XXS.gguf.part4of4) | i1-IQ3_XXS | 153.0 | lower quality |
53
  | [PART 1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-IQ3_M.gguf.part4of4) | i1-IQ3_M | 173.6 | |
54
+ | [P1](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/AI21-Jamba-Large-1.5-i1-GGUF/resolve/main/AI21-Jamba-Large-1.5.i1-Q4_K_S.gguf.part5of5) | i1-Q4_K_S | 226.3 | optimal size/speed/quality |
55
 
56
  Here is a handy graph by ikawrakow comparing some lower-quality quant
57
  types (lower is better):