This is Anima Base v1.0 merged with Turbo LoRA v0.2, optimized using SDNQ with INT8 dynamic quantization and Hadamard Rotation.

Downloads last month
-
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SamuelTallet/Anima-v1.0-Turbo-v0.2-SDNQ-8bit-dynamic-hadamard

Quantized
(23)
this model