GPTQ Q8 quantized version of DeepSeek R1 Distill 7B under Apache 2.0 license. Note, this version is not compatible with ExLlamaV2, but does work with V1 or Transformers. Enjoy

Downloads last month
191
Safetensors
Model size
2.87B params
Tensor type
I32
·
FP16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Akashium/DeepSeek-R1-Distill-Llama-8B-GPTQ

Quantized
(150)
this model