mradermacher
commited on
Commit
•
a5fefa6
1
Parent(s):
7c2cd48
auto-patch README.md
Browse files
README.md
CHANGED
@@ -27,7 +27,6 @@ tags:
|
|
27 |
weighted/imatrix quants of https://huggingface.co/theprint/ReWiz-Qwen-2.5-14B
|
28 |
|
29 |
<!-- provided-files -->
|
30 |
-
static quants are available at https://huggingface.co/mradermacher/ReWiz-Qwen-2.5-14B-GGUF
|
31 |
## Usage
|
32 |
|
33 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
@@ -40,30 +39,30 @@ more details, including on how to concatenate multi-part files.
|
|
40 |
|
41 |
| Link | Type | Size/GB | Notes |
|
42 |
|:-----|:-----|--------:|:------|
|
43 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
44 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
45 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
46 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
47 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
48 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
49 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
50 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
51 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
52 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
53 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
54 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
55 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
56 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
57 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
58 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
59 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
60 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
61 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
62 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
63 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
64 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
65 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
66 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
67 |
|
68 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
69 |
types (lower is better):
|
|
|
27 |
weighted/imatrix quants of https://huggingface.co/theprint/ReWiz-Qwen-2.5-14B
|
28 |
|
29 |
<!-- provided-files -->
|
|
|
30 |
## Usage
|
31 |
|
32 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
39 |
|
40 |
| Link | Type | Size/GB | Notes |
|
41 |
|:-----|:-----|--------:|:------|
|
42 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.7 | for the desperate |
|
43 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ1_M.gguf) | i1-IQ1_M | 4.0 | mostly desperate |
|
44 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 4.4 | |
|
45 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.8 | |
|
46 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ2_S.gguf) | i1-IQ2_S | 5.1 | |
|
47 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ2_M.gguf) | i1-IQ2_M | 5.5 | |
|
48 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q2_K.gguf) | i1-Q2_K | 5.9 | IQ3_XXS probably better |
|
49 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 6.0 | lower quality |
|
50 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 6.5 | |
|
51 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 6.8 | IQ3_XS probably better |
|
52 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ3_S.gguf) | i1-IQ3_S | 6.8 | beats Q3_K* |
|
53 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ3_M.gguf) | i1-IQ3_M | 7.0 | |
|
54 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 7.4 | IQ3_S probably better |
|
55 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 8.0 | IQ3_M probably better |
|
56 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 8.2 | |
|
57 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q4_0_4_4.gguf) | i1-Q4_0_4_4 | 8.6 | fast on arm, low quality |
|
58 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q4_0_4_8.gguf) | i1-Q4_0_4_8 | 8.6 | fast on arm+i8mm, low quality |
|
59 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q4_0_8_8.gguf) | i1-Q4_0_8_8 | 8.6 | fast on arm+sve, low quality |
|
60 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q4_0.gguf) | i1-Q4_0 | 8.6 | fast, low quality |
|
61 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 8.7 | optimal size/speed/quality |
|
62 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 9.1 | fast, recommended |
|
63 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 10.4 | |
|
64 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 10.6 | |
|
65 |
+
| [GGUF](https://huggingface.co/mradermacher/rewiz-qwen-2.5-14b-i1-GGUF/resolve/main/ReWiz-Qwen-2.5-14B.i1-Q6_K.gguf) | i1-Q6_K | 12.2 | practically like static Q6_K |
|
66 |
|
67 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
68 |
types (lower is better):
|