mradermacher
commited on
auto-patch README.md
Browse files
README.md
CHANGED
@@ -18,7 +18,7 @@ tags:
|
|
18 |
static quants of https://huggingface.co/CultriX/Qwen2.5-14B-Unity
|
19 |
|
20 |
<!-- provided-files -->
|
21 |
-
weighted/imatrix quants
|
22 |
## Usage
|
23 |
|
24 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -34,7 +34,14 @@ more details, including on how to concatenate multi-part files.
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q2_K.gguf) | Q2_K | 5.9 | |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
|
|
|
|
|
37 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
|
|
|
|
|
|
|
|
|
|
|
38 |
|
39 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
40 |
types (lower is better):
|
|
|
18 |
static quants of https://huggingface.co/CultriX/Qwen2.5-14B-Unity
|
19 |
|
20 |
<!-- provided-files -->
|
21 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-i1-GGUF
|
22 |
## Usage
|
23 |
|
24 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
34 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q2_K.gguf) | Q2_K | 5.9 | |
|
35 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q3_K_S.gguf) | Q3_K_S | 6.8 | |
|
36 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q3_K_M.gguf) | Q3_K_M | 7.4 | lower quality |
|
37 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q3_K_L.gguf) | Q3_K_L | 8.0 | |
|
38 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.IQ4_XS.gguf) | IQ4_XS | 8.3 | |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q4_K_S.gguf) | Q4_K_S | 8.7 | fast, recommended |
|
40 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q4_K_M.gguf) | Q4_K_M | 9.1 | fast, recommended |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q5_K_S.gguf) | Q5_K_S | 10.4 | |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q5_K_M.gguf) | Q5_K_M | 10.6 | |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q6_K.gguf) | Q6_K | 12.2 | very good quality |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-14B-Unity-GGUF/resolve/main/Qwen2.5-14B-Unity.Q8_0.gguf) | Q8_0 | 15.8 | fast, best quality |
|
45 |
|
46 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
47 |
types (lower is better):
|