GGUF models by TeichAI
60 GGUF models quantized by TeichAI on Hugging Face. Sizes run from 20M to 32.8B parameters. The longest trained context is 256K tokens.
About TeichAI on Hugging Face
TeichAI has published 60 GGUF models that ggufmodels.com tracks, across families such as Qwen, DeepSeek and Gemma. The most downloaded are Qwen3 14B Claude 4.5 Opus High Reasoning Distill, GLM 4.7 Flash Claude Opus 4.5 High Reasoning Distill and Qwen3.8 27B Fable Distill.
The quants TeichAI publishes most often are Q8_0 (56), Q4_K_M (49), Q3_K_M (47) and BF16 (47). Their Q4_K_M files range from 2.5 to 19.8 GB. Parameter counts run from 20M to 32.8B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has TeichAI published?
60 models are listed here, mainly from the Qwen, DeepSeek and Gemma families. The most downloaded is Qwen3 14B Claude 4.5 Opus High Reasoning Distill.
Which quants does TeichAI publish?
The most common are Q8_0 (56 models), Q4_K_M (49 models), Q3_K_M (47 models) and BF16 (47 models).