GGUF models by AbteeXAILab
71 GGUF models quantized by AbteeXAILab on Hugging Face. Sizes run from 135M to 671B parameters. The longest trained context is 1024K tokens.
About AbteeXAILab on Hugging Face
AbteeXAILab has published 71 GGUF models that ggufmodels.com tracks, across families such as Qwen, DeepSeek and Phi. The most downloaded are lumynax coder deepseek v2 lite 16b, lumynax multimodal kimi vl a3b thinking and lumynax infused mistral small text.
The quants AbteeXAILab publishes most often are Q4_K_M (61), F16 (4), Q8_0 (3) and TQ1_0 (1). Their Q4_K_M files range from 0.1 to 404.5 GB. Parameter counts run from 135M to 671B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has AbteeXAILab published?
71 models are listed here, mainly from the Qwen, DeepSeek and Phi families. The most downloaded is lumynax coder deepseek v2 lite 16b.
Which quants does AbteeXAILab publish?
The most common are Q4_K_M (61 models), F16 (4 models), Q8_0 (3 models) and TQ1_0 (1 models).