DeepSeek-R1-Distill-Llama-70B-Science-Q4_K_M-GGUF

Description

DeepSeek-R1-Distill-Llama-70B-Science-Q4_K_M-GGUF is an open-weight text-generation model with roughly 70B parameters published by ErikFeng on the Hugging Face Hub. It has 339 downloads. Runs with llama.cpp.

Categories

• Research
• Productivity

Tags

• llama.cpp
• quantization
• q4_k_m
• deepseek-r1
• reasoning
• mathematics
• MetaMathQA
• importance-matrix

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: llama.cpp
• 70B parameters