auto-patch README.md
Browse files
README.md
CHANGED
|
@@ -210,7 +210,20 @@ more details, including on how to concatenate multi-part files.
|
|
| 210 |
|
| 211 |
| Link | Type | Size/GB | Notes |
|
| 212 |
|:-----|:-----|--------:|:------|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 213 |
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part4of4) | i1-Q2_K | 149.4 | IQ3_XXS probably better |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 214 |
|
| 215 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 216 |
types (lower is better):
|
|
|
|
| 210 |
|
| 211 |
| Link | Type | Size/GB | Notes |
|
| 212 |
|:-----|:-----|--------:|:------|
|
| 213 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ1_M.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ1_M.gguf.part2of2) | i1-IQ1_M | 93.6 | mostly desperate |
|
| 214 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_XXS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_XXS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_XXS.gguf.part3of3) | i1-IQ2_XXS | 107.4 | |
|
| 215 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_XS.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_XS.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_XS.gguf.part3of3) | i1-IQ2_XS | 119.4 | |
|
| 216 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_M.gguf.part1of3) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_M.gguf.part2of3) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ2_M.gguf.part3of3) | i1-IQ2_M | 136.8 | |
|
| 217 |
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q2_K.gguf.part4of4) | i1-Q2_K | 149.4 | IQ3_XXS probably better |
|
| 218 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_XXS.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_XXS.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_XXS.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_XXS.gguf.part4of4) | i1-IQ3_XXS | 155.9 | lower quality |
|
| 219 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_S.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_S.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_S.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_S.gguf.part4of4) | i1-Q3_K_S | 175.3 | IQ3_XS probably better |
|
| 220 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ3_M.gguf.part4of4) | i1-IQ3_M | 181.8 | |
|
| 221 |
+
| [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_M.gguf.part1of4) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_M.gguf.part2of4) [PART 3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_M.gguf.part3of4) [PART 4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_M.gguf.part4of4) | i1-Q3_K_M | 195.5 | IQ3_S probably better |
|
| 222 |
+
| [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_L.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_L.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_L.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_L.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q3_K_L.gguf.part5of5) | i1-Q3_K_L | 212.9 | IQ3_M probably better |
|
| 223 |
+
| [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ4_XS.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ4_XS.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ4_XS.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ4_XS.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-IQ4_XS.gguf.part5of5) | i1-IQ4_XS | 216.7 | |
|
| 224 |
+
| [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_S.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_S.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_S.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_S.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_S.gguf.part5of5) | i1-Q4_K_S | 230.6 | optimal size/speed/quality |
|
| 225 |
+
| [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_M.gguf.part1of5) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_M.gguf.part2of5) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_M.gguf.part3of5) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_M.gguf.part4of5) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q4_K_M.gguf.part5of5) | i1-Q4_K_M | 243.2 | fast, recommended |
|
| 226 |
+
| [P1](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q6_K.gguf.part1of7) [P2](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q6_K.gguf.part2of7) [P3](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q6_K.gguf.part3of7) [P4](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q6_K.gguf.part4of7) [P5](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q6_K.gguf.part5of7) [P6](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q6_K.gguf.part6of7) [P7](https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3.1-405B-Instruct.i1-Q6_K.gguf.part7of7) | i1-Q6_K | 333.0 | practically like static Q6_K |
|
| 227 |
|
| 228 |
Here is a handy graph by ikawrakow comparing some lower-quality quant
|
| 229 |
types (lower is better):
|