Hugging Face's logo

mradermacher
/
Mahou-1.3-gemma2-9B-i1-GGUF

Transformers
GGUF
English
Inference Endpoints
imatrix
conversational
Model card Files Community
1
mradermacher commited on
Commit
5c87363
•
1 Parent(s): d2b109f

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -21
README.md CHANGED
@@ -33,27 +33,27 @@ more details, including on how to concatenate multi-part files.
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
37
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate |
38
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | |
39
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | |
40
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | |
41
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | |
42
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality |
43
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |
44
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | |
45
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* |
46
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better |
47
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | |
48
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better |
49
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better |
50
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | |
51
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality |
52
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |
53
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended |
54
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | |
55
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | |
56
- | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):
 
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate |
38
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |
44
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | |
45
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* |
46
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better |
47
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | |
48
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better |
49
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | |
51
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality |
52
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |
53
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended |
54
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | |
55
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | |
56
+ | [GGUF](https://huggingface.co/mradermacher/Mahou-1.3-gemma2-9B-i1-GGUF/resolve/main/Mahou-1.3-gemma2-9B.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K |
57
 
58
  Here is a handy graph by ikawrakow comparing some lower-quality quant
59
  types (lower is better):