🤗 Hugging Face | 🤖 ModelScope | 🐙 OpenRouter
Ling-3.0-flash is our next-generation native hybrid reasoning model. Operating with 124B total and 5.1B active parameters (~12.4% and ~8.1% of our previous 1T-class flagship Ring-2.6-1T), Ling-3.0-flash matches or outperforms its predecessor across key benchmarks.
Find more details in the original model card: https://huggingface.co/inclusionAI/Ling-3.0-flash
Q4_K_M/Ling-3.0-flash-Q4_K_M-00001-of-00002.gguf 50 GBQ4_K_M/Ling-3.0-flash-Q4_K_M-00002-of-00002.gguf 27 GBQ5_K_M/Ling-3.0-flash-Q5_K_M-00001-of-00002.gguf 49 GBQ5_K_M/Ling-3.0-flash-Q5_K_M-00002-of-00002.gguf 41 GBQ6_K/Ling-3.0-flash-Q6_K-00001-of-00003.gguf 50 GBQ6_K/Ling-3.0-flash-Q6_K-00002-of-00003.gguf 50 GBQ6_K/Ling-3.0-flash-Q6_K-00003-of-00003.gguf 5.0 GBQ8_0/Ling-3.0-flash-Q8_0-00001-of-00003.gguf 49 GBQ8_0/Ling-3.0-flash-Q8_0-00002-of-00003.gguf 49 GBQ8_0/Ling-3.0-flash-Q8_0-00003-of-00003.gguf 37 GBBF16/Ling-3.0-flash-BF16-00001-of-00006.gguf 50 GBBF16/Ling-3.0-flash-BF16-00003-of-00006.gguf 48 GBBF16/Ling-3.0-flash-BF16-00004-of-00006.gguf 48 GBBF16/Ling-3.0-flash-BF16-00005-of-00006.gguf 48 GBBF16/Ling-3.0-flash-BF16-00002-of-00006.gguf 48 GBBF16/Ling-3.0-flash-BF16-00006-of-00006.gguf 12 GB