GGUF models by Melvin56
62 GGUF models quantized by Melvin56 on Hugging Face. Sizes run from 494M to 10.3B parameters. The longest trained context is 128K tokens.
QW
Rombo LLM V2.5 Qwen 3b
Qwen · Melvin56
Params3.4B
Context32K
Smallest2.0 GB
QW
Rombo LLM V2.5 Qwen 3b
Qwen · Melvin56
Params3.4B
Context32K
Smallest2.4 GB