auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -32,8 +32,18 @@ more details, including on how to concatenate multi-part files.
|
|
| 32 |
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
| 35 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
|
|
|
|
|
|
|
| 36 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
|
| 38 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 39 |
types (lower is better):
|
|
|
|
| 32 |
|
| 33 |
| Link | Type | Size/GB | Notes |
|
| 34 |
|:-----|:-----|--------:|:------|
|
| 35 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-IQ1_M.gguf) | i1-IQ1_M | 8.0 | mostly desperate |
|
| 36 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-IQ2_M.gguf) | i1-IQ2_M | 11.4 | |
|
| 37 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q2_K_S.gguf) | i1-Q2_K_S | 11.6 | very low quality |
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q2_K.gguf) | i1-Q2_K | 12.4 | IQ3_XXS probably better |
|
| 39 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 12.9 | lower quality |
|
| 40 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q3_K_S.gguf) | i1-Q3_K_S | 14.5 | IQ3_XS probably better |
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-IQ3_M.gguf) | i1-IQ3_M | 14.9 | |
|
| 42 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q3_K_M.gguf) | i1-Q3_K_M | 16.0 | IQ3_S probably better |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-IQ4_XS.gguf) | i1-IQ4_XS | 17.8 | |
|
| 44 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q4_K_S.gguf) | i1-Q4_K_S | 18.9 | optimal size/speed/quality |
|
| 45 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q4_K_M.gguf) | i1-Q4_K_M | 20.0 | fast, recommended |
|
| 46 |
+
| [GGUF](https://huggingface.co/mradermacher/Qwen2.5-32b-RP-Ink-i1-GGUF/resolve/main/Qwen2.5-32b-RP-Ink.i1-Q6_K.gguf) | i1-Q6_K | 27.0 | practically like static Q6_K |
|
| 47 |
|
| 48 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 49 |
types (lower is better):
|