GGUF models by lainlives
36 GGUF models quantized by lainlives on Hugging Face. Sizes run from 752M to 30.5B parameters. The longest trained context is 1024K tokens.
About lainlives on Hugging Face
lainlives has published 36 GGUF models that ggufmodels.com tracks, across families such as Qwen, Spark and Exp. The most downloaded are Qwen3 Coder 30B A3B IT Heretic, Qwen3.5 9B Claude 4.6 HighIQ INSTRUCT HERETIC UNCENSORED and Qwen3 Coder 30B A3B Instruct_Pruned_REAP 15B A3B SafeTensors.
The quants lainlives publishes most often are Q8_0 (23), Q4_K_M (18), BF16 (18) and Q5_0 (17). Their Q4_K_M files range from 0.5 to 18.6 GB. Parameter counts run from 752M to 30.5B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has lainlives published?
36 models are listed here, mainly from the Qwen, Spark and Exp families. The most downloaded is Qwen3 Coder 30B A3B IT Heretic.
Which quants does lainlives publish?
The most common are Q8_0 (23 models), Q4_K_M (18 models), BF16 (18 models) and Q5_0 (17 models).