Hugging Face's logo

mradermacher
/
gemma-2-9b-it-yessir-5000-i1-GGUF

Transformers
GGUF
English
trl
sft
Generated from Trainer
Inference Endpoints
imatrix
conversational
Model card Files Community
mradermacher commited on
Commit
a450e5b
·
verified ·
1 Parent(s): b2706a6

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md CHANGED
@@ -33,9 +33,30 @@ more details, including on how to concatenate multi-part files.
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
 
 
 
 
 
 
 
 
36
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |
 
 
 
37
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | |
 
 
 
 
 
38
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |
 
 
 
 
 
39
 
40
  Here is a handy graph by ikawrakow comparing some lower-quality quant
41
  types (lower is better):
 
33
 
34
  | Link | Type | Size/GB | Notes |
35
  |:-----|:-----|--------:|:------|
36
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ1_S.gguf) | i1-IQ1_S | 2.5 | for the desperate |
37
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ1_M.gguf) | i1-IQ1_M | 2.6 | mostly desperate |
38
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.9 | |
39
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ2_XS.gguf) | i1-IQ2_XS | 3.2 | |
40
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ2_S.gguf) | i1-IQ2_S | 3.3 | |
41
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ2_M.gguf) | i1-IQ2_M | 3.5 | |
42
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q2_K_S.gguf) | i1-Q2_K_S | 3.7 | very low quality |
43
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.9 | lower quality |
44
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q2_K.gguf) | i1-Q2_K | 3.9 | IQ3_XXS probably better |
45
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ3_XS.gguf) | i1-IQ3_XS | 4.2 | |
46
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ3_S.gguf) | i1-IQ3_S | 4.4 | beats Q3_K* |
47
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q3_K_S.gguf) | i1-Q3_K_S | 4.4 | IQ3_XS probably better |
48
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ3_M.gguf) | i1-IQ3_M | 4.6 | |
49
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.9 | IQ3_S probably better |
50
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q3_K_L.gguf) | i1-Q3_K_L | 5.2 | IQ3_M probably better |
51
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ4_XS.gguf) | i1-IQ4_XS | 5.3 | |
52
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-IQ4_NL.gguf) | i1-IQ4_NL | 5.5 | prefer IQ4_XS |
53
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q4_0.gguf) | i1-Q4_0 | 5.6 | fast, low quality |
54
  | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q4_K_S.gguf) | i1-Q4_K_S | 5.6 | optimal size/speed/quality |
55
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.9 | fast, recommended |
56
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q4_1.gguf) | i1-Q4_1 | 6.1 | |
57
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q5_K_S.gguf) | i1-Q5_K_S | 6.6 | |
58
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q5_K_M.gguf) | i1-Q5_K_M | 6.7 | |
59
+ | [GGUF](https://huggingface.co/mradermacher/gemma-2-9b-it-yessir-5000-i1-GGUF/resolve/main/gemma-2-9b-it-yessir-5000.i1-Q6_K.gguf) | i1-Q6_K | 7.7 | practically like static Q6_K |
60
 
61
  Here is a handy graph by ikawrakow comparing some lower-quality quant
62
  types (lower is better):