Hammer2.1-GGUF
Collection
4 items
•
Updated
Original Model : https://huggingface.co/MadeAgents/Hammer2.1-1.5b
All quants are made using the imatrix option.
Model | Size (GB) |
---|---|
Q2_K_S | 0.63 |
Q2_K | 0.67 |
Q3_K_M | 0.82 |
Q3_K_M | 0.82 |
Q4_0 | 0.93 |
Q4_K_M | 0.98 |
Q5_K_M | 1.12 |
Q6_K | 1.27 |
Q8_0 | 1.64 |
F16 | 3.08 |
Base model
Qwen/Qwen2.5-1.5B