🦙 Automatic GGUF Quantization for Ursa_Minor

This space automatically creates quantized GGUF versions of the Sculptor-AI/Ursa_Minor model whenever it's updated.

Loading status...

Quantization Status

Quantization Status
Type	Size (GB)	Notes	Status
Q3_K_S	0.8	fast, best quality	Not processed

Type	Size (GB)	Notes	Status
Q2_K	0.8		Not processed
Q3_K_S	0.9		Not processed
Q3_K_M	0.9	lower quality	Not processed
Q3_K_L	1		Not processed
IQ4_XS	1		Not processed
Q4_K_S	1	fast, recommended	Not processed
Q4_K_M	1.1	fast, recommended	Not processed
Q5_K_S	1.2		Not processed
Q5_K_M	1.2		Not processed
Q6_K	1.4	very good quality	Not processed
Q8_0	1.7	fast, best quality	Not processed
f16	3.2	16 bpw, overkill	Not processed