auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -60,8 +60,14 @@ more details, including on how to concatenate multi-part files.
|
|
| 60 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
|
| 61 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
|
| 62 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
|
|
|
|
| 63 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
|
| 64 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 67 |
types (lower is better):
|
|
|
|
| 60 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q3_K_S.gguf) | Q3_K_S | 3.6 | |
|
| 61 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
|
| 62 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
|
| 63 |
+
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
|
| 64 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
|
| 65 |
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
|
| 66 |
+
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
|
| 67 |
+
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
|
| 68 |
+
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
|
| 69 |
+
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
|
| 70 |
+
| [GGUF](https://huggingface.co/mradermacher/prettybird_bce_basic_coder_8b-GGUF/resolve/main/prettybird_bce_basic_coder_8b.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
|
| 71 |
|
| 72 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 73 |
types (lower is better):
|