Hugging Face's logo

mradermacher
/
CodeGemma-2b-GGUF

Transformers
GGUF
English
code
gemma
Model card Files
xet
 Community
mradermacher commited on
Commit
2c25021
·
verified ·
1 Parent(s): 9e27b12

auto-patch README.md

Browse files
Files changed (1) hide show
  1. README.md +14 -14
README.md CHANGED
@@ -21,7 +21,7 @@ tags:
21
  static quants of https://huggingface.co/TechxGenus/CodeGemma-2b
22
 
23
  <!-- provided-files -->
24
- weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion.
25
  ## Usage
26
 
27
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
@@ -34,19 +34,19 @@ more details, including on how to concatenate multi-part files.
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q2_K.gguf) | Q2_K | 2.4 | |
38
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q3_K_S.gguf) | Q3_K_S | 2.7 | |
39
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality |
40
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q3_K_L.gguf) | Q3_K_L | 3.0 | |
41
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.IQ4_XS.gguf) | IQ4_XS | 3.1 | |
42
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q4_0_4_4.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.2 | fast on arm, low quality |
43
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q4_K_S.gguf) | Q4_K_S | 3.2 | fast, recommended |
44
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q4_K_M.gguf) | Q4_K_M | 3.4 | fast, recommended |
45
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q5_K_S.gguf) | Q5_K_S | 3.7 | |
46
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q5_K_M.gguf) | Q5_K_M | 3.8 | |
47
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q6_K.gguf) | Q6_K | 4.2 | very good quality |
48
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.Q8_0.gguf) | Q8_0 | 5.4 | fast, best quality |
49
- | [PART 1](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/CodeGemma-2b.f16.gguf) [PART 2](https://huggingface.co/mradermacher/codegemma-2b-GGUF/resolve/main/codegemma-2b.f16.gguf) | f16 | 10.1 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):
 
21
  static quants of https://huggingface.co/TechxGenus/CodeGemma-2b
22
 
23
  <!-- provided-files -->
24
+ weighted/imatrix quants are available at https://huggingface.co/mradermacher/CodeGemma-2b-i1-GGUF
25
  ## Usage
26
 
27
  If you are unsure how to use GGUF files, refer to one of [TheBloke's
 
34
 
35
  | Link | Type | Size/GB | Notes |
36
  |:-----|:-----|--------:|:------|
37
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q2_K.gguf) | Q2_K | 2.4 | |
38
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q3_K_S.gguf) | Q3_K_S | 2.7 | |
39
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q3_K_M.gguf) | Q3_K_M | 2.9 | lower quality |
40
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q3_K_L.gguf) | Q3_K_L | 3.0 | |
41
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.IQ4_XS.gguf) | IQ4_XS | 3.1 | |
42
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q4_0_4_4.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q4_0_4_4.gguf) | Q4_0_4_4 | 3.2 | fast on arm, low quality |
43
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q4_K_S.gguf) | Q4_K_S | 3.2 | fast, recommended |
44
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q4_K_M.gguf) | Q4_K_M | 3.4 | fast, recommended |
45
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q5_K_S.gguf) | Q5_K_S | 3.7 | |
46
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q5_K_M.gguf) | Q5_K_M | 3.8 | |
47
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q6_K.gguf) | Q6_K | 4.2 | very good quality |
48
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.Q8_0.gguf) | Q8_0 | 5.4 | fast, best quality |
49
+ | [PART 1](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/CodeGemma-2b.f16.gguf) [PART 2](https://huggingface.co/mradermacher/CodeGemma-2b-GGUF/resolve/main/codegemma-2b.f16.gguf) | f16 | 10.1 | 16 bpw, overkill |
50
 
51
  Here is a handy graph by ikawrakow comparing some lower-quality quant
52
  types (lower is better):