mradermacher
commited on
Commit
•
1acb297
1
Parent(s):
b1face2
auto-patch README.md
Browse files
README.md
CHANGED
@@ -26,7 +26,7 @@ tags:
|
|
26 |
static quants of https://huggingface.co/prithivMLmods/QwQ-LCoT-3B-Instruct
|
27 |
|
28 |
<!-- provided-files -->
|
29 |
-
weighted/imatrix quants
|
30 |
## Usage
|
31 |
|
32 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -43,9 +43,11 @@ more details, including on how to concatenate multi-part files.
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | |
|
|
|
46 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | |
|
|
|
49 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality |
|
51 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.f16.gguf) | f16 | 6.3 | 16 bpw, overkill |
|
|
|
26 |
static quants of https://huggingface.co/prithivMLmods/QwQ-LCoT-3B-Instruct
|
27 |
|
28 |
<!-- provided-files -->
|
29 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-i1-GGUF
|
30 |
## Usage
|
31 |
|
32 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q3_K_S.gguf) | Q3_K_S | 1.6 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q3_K_M.gguf) | Q3_K_M | 1.7 | lower quality |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q3_K_L.gguf) | Q3_K_L | 1.8 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.IQ4_XS.gguf) | IQ4_XS | 1.9 | |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q4_K_S.gguf) | Q4_K_S | 1.9 | fast, recommended |
|
48 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q4_K_M.gguf) | Q4_K_M | 2.0 | fast, recommended |
|
49 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q5_K_S.gguf) | Q5_K_S | 2.3 | |
|
50 |
+
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q5_K_M.gguf) | Q5_K_M | 2.3 | |
|
51 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q6_K.gguf) | Q6_K | 2.6 | very good quality |
|
52 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.Q8_0.gguf) | Q8_0 | 3.4 | fast, best quality |
|
53 |
| [GGUF](https://huggingface.co/mradermacher/QwQ-LCoT-3B-Instruct-GGUF/resolve/main/QwQ-LCoT-3B-Instruct.f16.gguf) | f16 | 6.3 | 16 bpw, overkill |
|