GGUF models by Guilherme34
89 GGUF models quantized by Guilherme34 on Hugging Face. Sizes run from 4M to 406B parameters. The longest trained context is 256K tokens.
About Guilherme34 on Hugging Face
Guilherme34 has published 89 GGUF models that ggufmodels.com tracks, across families such as Samantha, Firefly and Qwen. The most downloaded are Medra4b Abliterated, Qwen_Qwen3.5 9B__project Jeva 9b_1791678248 and Firefly v4.
The quants Guilherme34 publishes most often are Q4_K_M (32), Q8_0 (22), Q6_K (15) and Q2_K (9). Their Q4_K_M files range from 0.8 to 243.1 GB. Parameter counts run from 4M to 406B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has Guilherme34 published?
89 models are listed here, mainly from the Samantha, Firefly and Qwen families. The most downloaded is Medra4b Abliterated.
Which quants does Guilherme34 publish?
The most common are Q4_K_M (32 models), Q8_0 (22 models), Q6_K (15 models) and Q2_K (9 models).