GGUF models by IntelligentEstate
48 GGUF models quantized by IntelligentEstate on Hugging Face. Sizes run from 1.54B to 14.8B parameters. The longest trained context is 986K tokens.
About IntelligentEstate on Hugging Face
IntelligentEstate has published 48 GGUF models that ggufmodels.com tracks, across families such as Qwen, DeepSeek and Veolu. The most downloaded are HammerHead 7b Q4 k m, VEGA A Rombos QwC2.5 7B iQ4 K M and Qwen3 4b FireFly Q8 0.
The quants IntelligentEstate publishes most often are Q8_0 (11), Q4_K_M (11), Q6_K (2) and Q5_K_S (2). Their Q4_K_M files range from 2.5 to 9.0 GB. Parameter counts run from 1.54B to 14.8B, and the longest trained context window is 986K tokens.
Frequently asked questions
What GGUF models has IntelligentEstate published?
48 models are listed here, mainly from the Qwen, DeepSeek and Veolu families. The most downloaded is HammerHead 7b Q4 k m.
Which quants does IntelligentEstate publish?
The most common are Q8_0 (11 models), Q4_K_M (11 models), Q6_K (2 models) and Q5_K_S (2 models).