GGUF models by Ramikan-BR
77 GGUF models quantized by Ramikan-BR on Hugging Face. Sizes run from 494M to 8.03B parameters. The longest trained context is 128K tokens.
About Ramikan-BR on Hugging Face
Ramikan-BR has published 77 GGUF models that ggufmodels.com tracks, across families such as Tinyllama, Qwen and Mini. The most downloaded are tinyllama-coder-py-4bit-v10, Qwen2 0.5B v22 and tinyllama-coder-py-v12.
The quants Ramikan-BR publishes most often are F16 (58), Q8_0 (45) and Q4_K_M (44). Their Q4_K_M files range from 0.4 to 4.9 GB. Parameter counts run from 494M to 8.03B, and the longest trained context window is 128K tokens.
Frequently asked questions
What GGUF models has Ramikan-BR published?
77 models are listed here, mainly from the Tinyllama, Qwen and Mini families. The most downloaded is tinyllama-coder-py-4bit-v10.
Which quants does Ramikan-BR publish?
The most common are F16 (58 models), Q8_0 (45 models) and Q4_K_M (44 models).