GGUF models by Anbeeld
43 GGUF models quantized by Anbeeld on Hugging Face. Sizes run from 296M to 4.2B parameters. The longest trained context is 1024K tokens.
About Anbeeld on Hugging Face
Anbeeld has published 43 GGUF models that ggufmodels.com tracks, across families such as Qwen, Kimi and Gemma. The most downloaded are GLM 5.3 Flash DFlash2, Qwen3.8 27B DFlash2 and Qwen3.6 35B A3B DFlash.
The quants Anbeeld publishes most often are Q3_K_M (43), Q2_K (43), BF16 (43) and Q8_0 (42). Their Q4_K_M files range from 0.2 to 2.5 GB. Parameter counts run from 296M to 4.2B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has Anbeeld published?
43 models are listed here, mainly from the Qwen, Kimi and Gemma families. The most downloaded is GLM 5.3 Flash DFlash2.
Which quants does Anbeeld publish?
The most common are Q3_K_M (43 models), Q2_K (43 models), BF16 (43 models) and Q8_0 (42 models).