Hugging Face's logo

mradermacher
/
zeta-2.1-i1-GGUF

Transformers
GGUF
English
text-generation-inference
edit-prediction
next-edit-suggestion
imatrix
Model card Files
xet
 Community
mradermacher commited on
Commit
d6156ea
·
verified ·
1 Parent(s): 20a89c0

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -43,11 +43,14 @@ more details, including on how to concatenate multi-part files.
43
  | Link | Type | Size/GB | Notes |
44
  |:-----|:-----|--------:|:------|
45
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
 
46
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better |
47
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality |
48
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | |
49
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better |
 
50
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality |
 
51
 
52
  Here is a handy graph by ikawrakow comparing some lower-quality quant
53
  types (lower is better):
 
43
  | Link | Type | Size/GB | Notes |
44
  |:-----|:-----|--------:|:------|
45
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.imatrix.gguf) | imatrix | 0.1 | imatrix file (for creating your own quants) |
46
+ | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-IQ2_M.gguf) | i1-IQ2_M | 3.2 | |
47
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-Q2_K.gguf) | i1-Q2_K | 3.4 | IQ3_XXS probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.5 | lower quality |
49
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-IQ3_M.gguf) | i1-IQ3_M | 4.0 | |
50
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.3 | IQ3_S probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.9 | prefer IQ4_XS |
52
  | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.9 | optimal size/speed/quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/zeta-2.1-i1-GGUF/resolve/main/zeta-2.1.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.2 | fast, recommended |
54
 
55
  Here is a handy graph by ikawrakow comparing some lower-quality quant
56
  types (lower is better):