satgeze/DeepSeek-v4.1-Flash-EXL3-2.0bpw-Ablit-EngramQ4-SM120-Dual-RTX-Pro-6000

Different architecture vs deepseek-ai/DeepSeek-V4.1-Flash. Different architecture: only 3923 of 96085/188245 tensors match by name and shape.

On the Hub · Downloads on Model Pulse