Hugging Face's logo

stduhpf
/
google-gemma-3-12b-it-qat-q4_0-gguf-small

GGUF
conversational
Model card Files Community
4
stduhpf commited on
Commit
7076258
·
verified ·
1 Parent(s): 80d3132

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ Here are some perplexity measurements:
16
  | Model | File size ↓ | PPL (wiki.text.raw) ↓ |
17
  | --- | --- | --- |
18
  | [iQ3_xs (bartowski)](https://huggingface.co/bartowski/google_gemma-3-12b-it-GGUF/blob/main/google_gemma-3-12b-it-IQ3_XS.gguf) | 5.21 GB |10.0755 +/- 0.08024 |
19
- | QAT Q4_0 + Q6_k embeddings | 6.89 GB | 9.2637 +/- 0.07216 |
20
  | [Q4_0 (bartowski)](https://huggingface.co/bartowski/google_gemma-3-12b-it-GGUF/blob/main/google_gemma-3-12b-it-Q4_0.gguf) | 6.91 GB | 9.5589 +/- 0.07527 |
21
  | [QAT Q4_0 (google)](https://huggingface.co/google/gemma-3-12b-it-qat-q4_0-gguf/blob/main/gemma-3-12b-it-q4_0.gguf) | 8.07 GB | 9.2565 +/- 0.07212 |
22
  | [Q5_K_S (bartowski)](https://huggingface.co/bartowski/google_gemma-3-12b-it-GGUF/blob/main/google_gemma-3-12b-it-Q5_K_S.gguf) | 8.23 GB | 9.8540 +/- 0.08016 |
 
16
  | Model | File size ↓ | PPL (wiki.text.raw) ↓ |
17
  | --- | --- | --- |
18
  | [iQ3_xs (bartowski)](https://huggingface.co/bartowski/google_gemma-3-12b-it-GGUF/blob/main/google_gemma-3-12b-it-IQ3_XS.gguf) | 5.21 GB |10.0755 +/- 0.08024 |
19
+ | [This model](https://huggingface.co/stduhpf/google-gemma-3-12b-it-qat-q4_0-gguf-small/blob/main/gemma-3-12b-it-q4_0_s.gguf) | 6.89 GB | 9.2637 +/- 0.07216 |
20
  | [Q4_0 (bartowski)](https://huggingface.co/bartowski/google_gemma-3-12b-it-GGUF/blob/main/google_gemma-3-12b-it-Q4_0.gguf) | 6.91 GB | 9.5589 +/- 0.07527 |
21
  | [QAT Q4_0 (google)](https://huggingface.co/google/gemma-3-12b-it-qat-q4_0-gguf/blob/main/gemma-3-12b-it-q4_0.gguf) | 8.07 GB | 9.2565 +/- 0.07212 |
22
  | [Q5_K_S (bartowski)](https://huggingface.co/bartowski/google_gemma-3-12b-it-GGUF/blob/main/google_gemma-3-12b-it-Q5_K_S.gguf) | 8.23 GB | 9.8540 +/- 0.08016 |