Llama.cpp Quantized based on this Llama.cpp MR big thanks to fairydreaming!

The quantization has been performed on my BF16 version DevQuasar/deepseek-ai.DeepSeek-V3-Base-bf16

Inference proof:

I'm doing this to 'Make knowledge free for everyone', using my personal time and resources.

If you want to support my efforts please visit my ko-fi page: https://ko-fi.com/devquasar

Also feel free to visit my website https://devquasar.com/

GGUF

Model size

671B params

Architecture

deepseek2

2-bit

3-bit

Inference Examples

Unable to determine this model's library. Check the docs .

Model tree for DevQuasar/deepseek-ai.DeepSeek-V3-Base-GGUF

Base model

Quantized

(2)

this model

Finetunes