mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ tags: []
|
|
16 |
static quants of https://huggingface.co/fiveflow/KoLlama-3-8B-Instruct-Mix
|
17 |
|
18 |
<!-- provided-files -->
|
19 |
-
weighted/imatrix quants
|
20 |
## Usage
|
21 |
|
22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -33,9 +33,11 @@ more details, including on how to concatenate multi-part files.
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
|
|
36 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
|
|
|
39 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|
|
|
16 |
static quants of https://huggingface.co/fiveflow/KoLlama-3-8B-Instruct-Mix
|
17 |
|
18 |
<!-- provided-files -->
|
19 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-i1-GGUF
|
20 |
## Usage
|
21 |
|
22 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
33 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_S.gguf) | Q3_K_S | 3.8 | |
|
34 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q3_K_L.gguf) | Q3_K_L | 4.4 | |
|
36 |
+
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.IQ4_XS.gguf) | IQ4_XS | 4.6 | |
|
37 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended |
|
38 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q5_K_S.gguf) | Q5_K_S | 5.7 | |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q5_K_M.gguf) | Q5_K_M | 5.8 | |
|
41 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q6_K.gguf) | Q6_K | 6.7 | very good quality |
|
42 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality |
|
43 |
| [GGUF](https://huggingface.co/mradermacher/KoLlama-3-8B-Instruct-Mix-GGUF/resolve/main/KoLlama-3-8B-Instruct-Mix.f16.gguf) | f16 | 16.2 | 16 bpw, overkill |
|