auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ tags:
|
|
| 19 |
static quants of https://huggingface.co/Qwen/Qwen2.5-32B-Instruct
|
| 20 |
|
| 21 |
<!-- provided-files -->
|
| 22 |
-
weighted/imatrix quants are available at https://huggingface.co/mradermacher/
|
| 23 |
## Usage
|
| 24 |
|
| 25 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
@@ -32,29 +32,29 @@ more details, including on how to concatenate multi-part files.
|
|
| 32 |
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
| 35 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 36 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 37 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 38 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 39 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 40 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 41 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 42 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 43 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 44 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 45 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 46 |
-
| [GGUF](https://huggingface.co/mradermacher/
|
| 47 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 48 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 49 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 50 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 51 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 52 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 53 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 54 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 55 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 56 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 57 |
-
| [PART 1](https://huggingface.co/mradermacher/
|
| 58 |
|
| 59 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 60 |
types (lower is better):
|
|
|
|
| 19 |
static quants of https://huggingface.co/Qwen/Qwen2.5-32B-Instruct
|
| 20 |
|
| 21 |
<!-- provided-files -->
|
| 22 |
+
weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-i1-GGUF
|
| 23 |
## Usage
|
| 24 |
|
| 25 |
If you are unsure how to use GGUF files, refer to one of [TheBloke's
|
|
|
|
| 32 |
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.IQ3_XS.gguf) | IQ3_XS | 13.8 | |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.IQ3_S.gguf) | IQ3_S | 14.5 | beats Q3_K* |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.IQ3_M.gguf) | IQ3_M | 14.9 | |
|
| 38 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q4_0.gguf) | Q4_0 | 18.7 | fast, low quality |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q4_0_4_4.gguf) | Q4_0_4_4 | 18.7 | fast on arm, low quality |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q4_0_4_8.gguf) | Q4_0_4_8 | 18.7 | fast on arm+i8mm, low quality |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q4_0_8_8.gguf) | Q4_0_8_8 | 18.7 | fast on arm+sve, low quality |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.IQ4_NL.gguf) | IQ4_NL | 18.9 | prefer IQ4_XS |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q4_1.gguf) | Q4_1 | 20.7 | |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q5_0.gguf) | Q5_0 | 22.7 | |
|
| 45 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q2_K.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q2_K.gguf) | Q2_K | 24.7 | |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q5_1.gguf) | Q5_1 | 24.7 | |
|
| 47 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q3_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q3_K_S.gguf) | Q3_K_S | 28.9 | |
|
| 48 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q3_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q3_K_M.gguf) | Q3_K_M | 32.0 | lower quality |
|
| 49 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q3_K_L.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q3_K_L.gguf) | Q3_K_L | 34.6 | |
|
| 50 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.IQ4_XS.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.IQ4_XS.gguf) | IQ4_XS | 35.8 | |
|
| 51 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q4_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q4_K_S.gguf) | Q4_K_S | 37.7 | fast, recommended |
|
| 52 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q4_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q4_K_M.gguf) | Q4_K_M | 39.8 | fast, recommended |
|
| 53 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q5_K_S.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q5_K_S.gguf) | Q5_K_S | 45.4 | |
|
| 54 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q5_K_M.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q5_K_M.gguf) | Q5_K_M | 46.6 | |
|
| 55 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q6_K.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q6_K.gguf) | Q6_K | 53.9 | very good quality |
|
| 56 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.SOURCE.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.SOURCE.gguf.part2of2) | SOURCE | 65.6 | source gguf, only provided when it was hard to come by |
|
| 57 |
+
| [PART 1](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/Qwen2.5-32B-Instruct.Q8_0.gguf) [PART 2](https://huggingface.co/mradermacher/Qwen2.5-32B-Instruct-GGUF/resolve/main/qwen2.5-32b-instruct.Q8_0.gguf) | Q8_0 | 69.7 | fast, best quality |
|
| 58 |
|
| 59 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 60 |
types (lower is better):
|