GGUF models by netcat420
231 GGUF models quantized by netcat420 on Hugging Face. Sizes run from 1.91B to 8.19B parameters. The longest trained context is 500K tokens.
About netcat420 on Hugging Face
netcat420 has published 231 GGUF models that ggufmodels.com tracks, across families such as Mfann, Qwen and Mfannv. The most downloaded are Qwen2.5 Coder Scholar 7B Abliterated MFANN Q4 0, qwen2.5 MFANN 7b SLERP V1.2 Q4 K M and MFANN3bv0.6.
The quants netcat420 publishes most often are Q4_K_M (44), Q4_K_S (36), Q6_K (23) and Q8_0 (22). Their Q4_K_M files range from 1.2 to 5.0 GB. Parameter counts run from 1.91B to 8.19B, and the longest trained context window is 500K tokens.
Frequently asked questions
What GGUF models has netcat420 published?
231 models are listed here, mainly from the Mfann, Qwen and Mfannv families. The most downloaded is Qwen2.5 Coder Scholar 7B Abliterated MFANN Q4 0.
Which quants does netcat420 publish?
The most common are Q4_K_M (44 models), Q4_K_S (36 models), Q6_K (23 models) and Q8_0 (22 models).