Llamacpp Quantizations of DeepSeek-V3-0324-MoE-Pruner-E192 by tflsxyy

All quants made with modification of llama.cpp based on bartowski1182-llama.cpp.

All quants made using imatrix option based on tflsxyy/DeepSeek-V3-0324-MoE-Pruner-imatrix.

IQ1_M / Q4_K / Q8_0 : 110.19 GiB(1.87 BPW)

IQ1_S / Q4_K / Q8_0 : 99.45 GiB (1.68 BPW)

GGUF

Model size

508B params

Architecture

deepseek2

Hardware compatibility

1-bit

Inference Providers NEW

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

Model tree for bobchenyx/DeepSeek-V3-0324-HFK-E192-GGUF

Base model

Quantized

(17)

this model