image/png

ExLlamaV2 BPW 6.0 quant of xxx777xxxASD/PrimaSumika-10.7B-128k (Fits in 12GB VRAM/42k context/4-bit cache)

Downloads last month
7
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Collection including xxx777xxxASD/PrimaSumika-10.7B-128k-bpw-6.0