GGUF models by neopolita
183 GGUF models quantized by neopolita on Hugging Face. Sizes run from 135M to 177B parameters. The longest trained context is 256K tokens.
About neopolita on Hugging Face
neopolita has published 183 GGUF models that ggufmodels.com tracks, across families such as Qwen, Llama and Yi. The most downloaded are Qwen3.8 Flash Next 99B A5B Niwaki 3bit, mistral 7b v0.1 and Qwen3.8-Flash-Next-102B-A5B-Niwaki-v2.4-3bit.
The quants neopolita publishes most often are Q4_K_M (156), Q8_0 (147), Q3_K_M (145) and Q2_K (145). Their Q4_K_M files range from 0.1 to 44.1 GB. Parameter counts run from 135M to 177B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has neopolita published?
183 models are listed here, mainly from the Qwen, Llama and Yi families. The most downloaded is Qwen3.8 Flash Next 99B A5B Niwaki 3bit.
Which quants does neopolita publish?
The most common are Q4_K_M (156 models), Q8_0 (147 models), Q3_K_M (145 models) and Q2_K (145 models).