mradermacher
commited on
Commit
•
a093a5a
1
Parent(s):
ade3683
auto-patch README.md
Browse files
README.md
CHANGED
@@ -38,12 +38,21 @@ more details, including on how to concatenate multi-part files.
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
|
|
|
|
|
|
|
|
|
41 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
|
|
|
42 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
|
|
|
|
|
43 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
|
44 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
|
|
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
|
46 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
|
|
|
47 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
|
48 |
|
49 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
@@ -63,6 +72,6 @@ questions you might have and/or if you want some other model quantized.
|
|
63 |
|
64 |
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
65 |
me use its servers and providing upgrades to my workstation to enable
|
66 |
-
this work in my free time.
|
67 |
|
68 |
<!-- end -->
|
|
|
38 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q3_K_M.gguf) | Q3_K_M | 3.9 | lower quality |
|
39 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q3_K_L.gguf) | Q3_K_L | 4.2 | |
|
40 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ4_XS.gguf) | IQ4_XS | 4.4 | |
|
41 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0.gguf) | Q4_0 | 4.5 | fast, low quality |
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0_4_4.gguf) | Q4_0_4_4 | 4.5 | fast on arm, low quality |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0_4_8.gguf) | Q4_0_4_8 | 4.5 | fast on arm+i8mm, low quality |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_0_8_8.gguf) | Q4_0_8_8 | 4.5 | fast on arm+sve, low quality |
|
45 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_K_S.gguf) | Q4_K_S | 4.6 | fast, recommended |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.IQ4_NL.gguf) | IQ4_NL | 4.6 | prefer IQ4_XS |
|
47 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_K_M.gguf) | Q4_K_M | 4.8 | fast, recommended |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q4_1.gguf) | Q4_1 | 5.0 | |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_0.gguf) | Q5_0 | 5.4 | |
|
50 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_K_S.gguf) | Q5_K_S | 5.4 | |
|
51 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_K_M.gguf) | Q5_K_M | 5.5 | |
|
52 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q5_1.gguf) | Q5_1 | 5.9 | |
|
53 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q6_K.gguf) | Q6_K | 6.4 | very good quality |
|
54 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.Q8_0.gguf) | Q8_0 | 8.2 | fast, best quality |
|
55 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.SOURCE.gguf) | SOURCE | 15.3 | source gguf, only provided when it was hard to come by |
|
56 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-7B-GGUF/resolve/main/Qwen2.5-7B.f16.gguf) | f16 | 15.3 | 16 bpw, overkill |
|
57 |
|
58 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
72 |
|
73 |
I thank my company, [nethype GmbH](https://www.nethype.de/), for letting
|
74 |
me use its servers and providing upgrades to my workstation to enable
|
75 |
+
this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to.
|
76 |
|
77 |
<!-- end -->
|