GGUF models by fevohh
56 GGUF models quantized by fevohh on Hugging Face. Sizes run from 135M to 8.03B parameters. The longest trained context is 256K tokens.
About fevohh on Hugging Face
fevohh has published 56 GGUF models that ggufmodels.com tracks, across families such as Genparser, Rayextract and Llama. The most downloaded are WorldParser 1903, RayExtract 0.5B v1 and GenParser 3B v1.1 1k Iter2.
The quants fevohh publishes most often are Q8_0 (55), F16 (52), Q5_K_M (23) and Q4_K_M (23). Their Q4_K_M files range from 0.1 to 2.0 GB. Parameter counts run from 135M to 8.03B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has fevohh published?
56 models are listed here, mainly from the Genparser, Rayextract and Llama families. The most downloaded is WorldParser 1903.
Which quants does fevohh publish?
The most common are Q8_0 (55 models), F16 (52 models), Q5_K_M (23 models) and Q4_K_M (23 models).