GGUF models by ddh0
65 GGUF models quantized by ddh0 on Hugging Face. Sizes run from 14M to 549B parameters. The longest trained context is 1024K tokens.
About ddh0 on Hugging Face
ddh0 has published 65 GGUF models that ggufmodels.com tracks, across families such as Mistral, GLM and Qwen. The most downloaded are DeepSeek V4 Flash Vision Exp Uncensored, MiMo-V2.6-Flash-MOPD and GLM-4.5-Air-Derestricted.
The quants ddh0 publishes most often are Q8_0 (30), BF16 (13), Q4_K_S (5) and Q3_K (5). Their Q4_K_M files range from 4.4 to 42.5 GB. Parameter counts run from 14M to 549B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has ddh0 published?
65 models are listed here, mainly from the Mistral, GLM and Qwen families. The most downloaded is DeepSeek V4 Flash Vision Exp Uncensored.
Which quants does ddh0 publish?
The most common are Q8_0 (30 models), BF16 (13 models), Q4_K_S (5 models) and Q3_K (5 models).