auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -38,15 +38,20 @@ more details, including on how to concatenate multi-part files.
|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
|
|
|
|
| 41 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
|
|
|
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
|
| 43 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
|
| 45 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
|
| 46 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
|
|
|
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
|
|
|
|
| 49 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
|
|
|
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
|
| 51 |
|
| 52 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
|
|
|
| 38 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q2_K_S.gguf) | i1-Q2_K_S | 2.9 | very low quality |
|
| 39 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q2_K.gguf) | i1-Q2_K | 3.1 | IQ3_XXS probably better |
|
| 40 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.2 | lower quality |
|
| 41 |
+
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.4 | |
|
| 42 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.6 | IQ3_XS probably better |
|
| 43 |
+
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ3_S.gguf) | i1-IQ3_S | 3.6 | beats Q3_K* |
|
| 44 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ3_M.gguf) | i1-IQ3_M | 3.7 | |
|
| 45 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q3_K_M.gguf) | i1-Q3_K_M | 3.9 | IQ3_S probably better |
|
| 46 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.2 | IQ3_M probably better |
|
| 47 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.3 | |
|
| 48 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-IQ4_NL.gguf) | i1-IQ4_NL | 4.5 | prefer IQ4_XS |
|
| 49 |
+
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q4_0.gguf) | i1-Q4_0 | 4.5 | fast, low quality |
|
| 50 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.6 | optimal size/speed/quality |
|
| 51 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q4_K_M.gguf) | i1-Q4_K_M | 4.8 | fast, recommended |
|
| 52 |
+
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q4_1.gguf) | i1-Q4_1 | 5.0 | |
|
| 53 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.4 | |
|
| 54 |
+
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.5 | |
|
| 55 |
| [GGUF](https://huggingface.co/mradermacher/Rombo-LLM-V2.5-Qwen-7b-i1-GGUF/resolve/main/Rombo-LLM-V2.5-Qwen-7b.i1-Q6_K.gguf) | i1-Q6_K | 6.4 | practically like static Q6_K |
|
| 56 |
|
| 57 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|