Views
No views yet
| Link | Type | Size/GB | Notes |
|---|---|---|---|
| GGUF | imatrix | 0.3 | imatrix file (for creating your own quants) |
| GGUF | i1-IQ1_S | 14.6 | for the desperate |
| GGUF | i1-IQ1_M | 16.1 | mostly desperate |
| GGUF | i1-IQ2_XXS | 18.6 | |
| GGUF | i1-IQ2_XS | 20.7 | |
| GGUF | i1-IQ2_S | 21.1 | |
| GGUF | i1-IQ2_M | 23.2 | |
| GGUF | i1-Q2_K_S | 24.0 | very low quality |
| GGUF | i1-Q2_K | 25.7 | IQ3_XXS probably better |
| GGUF | i1-IQ3_XXS | 27.0 | lower quality |
| GGUF | i1-IQ3_XS | 28.8 | |
| GGUF | i1-Q3_K_S | 30.3 | IQ3_XS probably better |
| GGUF | i1-IQ3_S | 30.3 | beats Q3_K* |
| GGUF | i1-IQ3_M | 30.9 | |
| GGUF | i1-Q3_K_M | 33.6 | IQ3_S probably better |
| GGUF | i1-Q3_K_L | 36.3 | IQ3_M probably better |
| GGUF | i1-IQ4_XS | 37.3 | |
| GGUF | i1-Q4_0 | 39.6 | fast, low quality |
| GGUF | i1-Q4_K_S | 39.8 | optimal size/speed/quality |
| GGUF | i1-Q4_K_M | 42.2 | fast, recommended |
| GGUF | i1-Q4_1 | 43.7 | |
| GGUF | i1-Q5_K_S | 48.0 | |
| GGUF | i1-Q5_K_M | 49.4 | |
| GGUF | i1-Q6_K | 57.1 | practically like static Q6_K |
