mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -30,8 +30,13 @@ more details, including on how to concatenate multi-part files.
|
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q2_K.gguf) | Q2_K | 3.9 | |
|
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
|
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
|
|
|
|
|
|
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
|
36 |
|
37 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
30 |
| Link | Type | Size/GB | Notes |
|
31 |
|:-----|:-----|--------:|:------|
|
32 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q2_K.gguf) | Q2_K | 3.9 | |
|
33 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q3_K_S.gguf) | Q3_K_S | 4.4 | |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q3_K_M.gguf) | Q3_K_M | 4.9 | lower quality |
|
35 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q3_K_L.gguf) | Q3_K_L | 5.2 | |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q4_K_S.gguf) | Q4_K_S | 5.6 | fast, recommended |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q4_K_M.gguf) | Q4_K_M | 5.9 | fast, recommended |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q6_K.gguf) | Q6_K | 7.7 | very good quality |
|
39 |
+
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.Q8_0.gguf) | Q8_0 | 9.9 | fast, best quality |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Gemmoy-9B-MK.I-GGUF/resolve/main/Gemmoy-9B-MK.I.f16.gguf) | f16 | 18.6 | 16 bpw, overkill |
|
41 |
|
42 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|