Expert pruning from 256 to 160

Attn: Q4_K

Experts: IQ1_S

Please refer to unsloth for running this model.

Downloads last month
232
GGUF
Model size
426B params
Architecture
deepseek2
Hardware compatibility
Log In to view the estimation

1-bit

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

Model tree for tflsxyy/DeepSeek-V3-0324-MoE-Pruner-E160-IQ1_S

Quantized
(14)
this model