GGUF models by Volko76
34 GGUF models quantized by Volko76 on Hugging Face. Sizes run from 268M to 284B parameters. The longest trained context is 1024K tokens.
About Volko76 on Hugging Face
Volko76 has published 34 GGUF models that ggufmodels.com tracks, across families such as Qwen, Opencoder and Lucie. The most downloaded are Qwen2.5 Coder 0.5B, Qwen2.5 Coder 32B Instruct AWQ and Qwen2.5 1.5B Instruct.
The quants Volko76 publishes most often are Q4_K_M (23), Q8_0 (19), Q5_K_M (18) and Q2_K (17). Their Q4_K_M files range from 0.4 to 39.7 GB. Parameter counts run from 268M to 284B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has Volko76 published?
34 models are listed here, mainly from the Qwen, Opencoder and Lucie families. The most downloaded is Qwen2.5 Coder 0.5B.
Which quants does Volko76 publish?
The most common are Q4_K_M (23 models), Q8_0 (19 models), Q5_K_M (18 models) and Q2_K (17 models).