| Q2_K |
5.36 GB |
Not recommended for most people. Very low quality. |
| Q2_K_L |
6.07 GB |
Not recommended for most people. Uses Q8_0 for output and embedding, and Q2_K for everything else. Very low quality. |
| Q2_K_XL |
7.42 GB |
Not recommended for most people. Uses F16 for output and embedding, and Q2_K for everything else. Very low quality. |
| Q3_K_S |
6.2 GB |
Not recommended for most people. Prefer any bigger Q3_K quantization. Low quality. |
| Q3_K_M |
6.82 GB |
Not recommended for most people. Low quality. |
| Q3_K_L |
7.36 GB |
Not recommended for most people. Low quality. |
| Q3_K_XL |
7.99 GB |
Not recommended for most people. Uses Q8_0 for output and embedding, and Q3_K_L for everything else. Low quality. |
| Q3_K_XXL |
9.35 GB |
Not recommended for most people. Uses F16 for output and embedding, and Q3_K_L for everything else. Low quality. |
| Q4_K_S |
7.98 GB |
Recommended. Slightly low quality. |
| Q4_K_M |
8.38 GB |
Recommended. Decent quality for most use cases. |
| Q4_K_L |
8.92 GB |
Recommended. Uses Q8_0 for output and embedding, and Q4_K_M for everything else. Decent quality. |
| Q4_K_XL |
10.28 GB |
Recommended. Uses F16 for output and embedding, and Q4_K_M for everything else. Decent quality. |
| Q5_K_S |
9.56 GB |
Recommended. High quality. |
| Q5_K_M |
9.79 GB |
Recommended. High quality. |
| Q5_K_L |
10.24 GB |
Recommended. Uses Q8_0 for output and embedding, and Q5_K_M for everything else. High quality. |
| Q5_K_XL |
11.6 GB |
Recommended. Uses F16 for output and embedding, and Q5_K_M for everything else. High quality. |
| Q6_K |
11.29 GB |
Recommended. Very high quality. |
| Q6_K_L |
11.64 GB |
Recommended. Uses Q8_0 for output and embedding, and Q6_K for everything else. Very high quality. |
| Q6_K_XL |
13.0 GB |
Recommended. Uses F16 for output and embedding, and Q6_K for everything else. Very high quality. |
| Q8_0 |
14.62 GB |
Recommended. Quality almost like F16. |
| Q8_K_XL |
15.98 GB |
Recommended. Uses F16 for output and embedding, and Q8_0 for everything else. Quality almost like F16. |
| F16 |
27.51 GB |
Not recommended. Overkill. Prefer Q8_0. |
| ORIGINAL (BF16) |
27.51 GB |
Not recommended. Overkill. Prefer Q8_0. |