GGUF models by bunnycore
161 GGUF models quantized by bunnycore on Hugging Face. Sizes run from 1M to 14.7B parameters. The longest trained context is 1024K tokens.
About bunnycore on Hugging Face
bunnycore has published 161 GGUF models that ggufmodels.com tracks, across families such as Llama, Qwen and Gemma. The most downloaded are LMF 2.5 2B Code, SuperMiniCPM5 2B Qween and MiniCPM5 2B Code.
The quants bunnycore publishes most often are Q5_K_M (57), IQ4_NL (27), Q4_K_M (24) and Q8_0 (15). Their Q4_K_M files range from 1.7 to 8.9 GB. Parameter counts run from 1M to 14.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has bunnycore published?
161 models are listed here, mainly from the Llama, Qwen and Gemma families. The most downloaded is LMF 2.5 2B Code.
Which quants does bunnycore publish?
The most common are Q5_K_M (57 models), IQ4_NL (27 models), Q4_K_M (24 models) and Q8_0 (15 models).