GGUF models by l3utterfly
51 GGUF models quantized by l3utterfly on Hugging Face. Sizes run from 1.1B to 16.5B parameters. The longest trained context is 1000K tokens.
About l3utterfly on Hugging Face
l3utterfly has published 51 GGUF models that ggufmodels.com tracks, across families such as Llama, Gemma and Phi. The most downloaded are Gemmasutra Mini 2B v1, Gemma 2 2b It and Impish_LLAMA_3B.
The quants l3utterfly publishes most often are Q2_K (45), F16 (45), Q8_0 (44) and Q6_K (44). Their Q4_K_M files range from 0.7 to 10.0 GB. Parameter counts run from 1.1B to 16.5B, and the longest trained context window is 1000K tokens.
Frequently asked questions
What GGUF models has l3utterfly published?
51 models are listed here, mainly from the Llama, Gemma and Phi families. The most downloaded is Gemmasutra Mini 2B v1.
Which quants does l3utterfly publish?
The most common are Q2_K (45 models), F16 (45 models), Q8_0 (44 models) and Q6_K (44 models).