GGUF models by BenevolenceMessiah
75 GGUF models quantized by BenevolenceMessiah on Hugging Face. Sizes run from 137M to 32.8B parameters. The longest trained context is 986K tokens.
About BenevolenceMessiah on Hugging Face
BenevolenceMessiah has published 75 GGUF models that ggufmodels.com tracks, across families such as Qwen, DeepSeek and Llama. The most downloaded are Replete-Coder-Llama3-8B, Qwen2.5 Coder 32B Instruct Abliterated and Phi 3 Mini 128k Instruct.
The quants BenevolenceMessiah publishes most often are Q8_0 (64), Q6_K (6), Q5_K_M (5) and Q5_K_S (4). Their Q4_K_M files range from 2.4 to 19.9 GB. Parameter counts run from 137M to 32.8B, and the longest trained context window is 986K tokens.
Frequently asked questions
What GGUF models has BenevolenceMessiah published?
75 models are listed here, mainly from the Qwen, DeepSeek and Llama families. The most downloaded is Replete-Coder-Llama3-8B.
Which quants does BenevolenceMessiah publish?
The most common are Q8_0 (64 models), Q6_K (6 models), Q5_K_M (5 models) and Q5_K_S (4 models).