auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -34,9 +34,18 @@ more details, including on how to concatenate multi-part files.
|
|
| 34 |
| Link | Type | Size/GB | Notes |
|
| 35 |
|:-----|:-----|--------:|:------|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q2_K.gguf) | Q2_K | 10.5 | |
|
|
|
|
| 37 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.IQ3_S.gguf) | IQ3_S | 12.3 | beats Q3_K* |
|
|
|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.IQ3_M.gguf) | IQ3_M | 12.6 | |
|
|
|
|
|
|
|
|
|
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q4_K_S.gguf) | Q4_K_S | 15.8 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q8_0.gguf) | Q8_0 | 29.0 | fast, best quality |
|
| 41 |
|
| 42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 34 |
| Link | Type | Size/GB | Notes |
|
| 35 |
|:-----|:-----|--------:|:------|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q2_K.gguf) | Q2_K | 10.5 | |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.IQ3_XS.gguf) | IQ3_XS | 11.7 | |
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.IQ3_S.gguf) | IQ3_S | 12.3 | beats Q3_K* |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q3_K_S.gguf) | Q3_K_S | 12.3 | |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.IQ3_M.gguf) | IQ3_M | 12.6 | |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q3_K_M.gguf) | Q3_K_M | 13.5 | lower quality |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q3_K_L.gguf) | Q3_K_L | 14.6 | |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.IQ4_XS.gguf) | IQ4_XS | 15.0 | |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q4_K_S.gguf) | Q4_K_S | 15.8 | fast, recommended |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q4_K_M.gguf) | Q4_K_M | 16.7 | fast, recommended |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q5_K_S.gguf) | Q5_K_S | 19.0 | |
|
| 47 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q5_K_M.gguf) | Q5_K_M | 19.5 | |
|
| 48 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q6_K.gguf) | Q6_K | 22.4 | very good quality |
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/Gemma-2-27B-Chinese-Chat-GGUF/resolve/main/Gemma-2-27B-Chinese-Chat.Q8_0.gguf) | Q8_0 | 29.0 | fast, best quality |
|
| 50 |
|
| 51 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|