GGUF models by RCorvalan
35 GGUF models quantized by RCorvalan on Hugging Face. Sizes run from 3.82B to 32.8B parameters. The longest trained context is 986K tokens.
About RCorvalan on Hugging Face
RCorvalan has published 35 GGUF models that ggufmodels.com tracks, across families such as Phi, Qwen and OLMo. The most downloaded are Qwen2.5 14B Instruct 1M, DeepSeek R1 Distill Llama 8B and DeepSeek R1 Distill Qwen 14B.
The quants RCorvalan publishes most often are Q4_K_M (8), Q8_0 (7), Q6_K (5) and Q2_K (4). Their Q4_K_M files range from 2.4 to 19.9 GB. Parameter counts run from 3.82B to 32.8B, and the longest trained context window is 986K tokens.
Frequently asked questions
What GGUF models has RCorvalan published?
35 models are listed here, mainly from the Phi, Qwen and OLMo families. The most downloaded is Qwen2.5 14B Instruct 1M.
Which quants does RCorvalan publish?
The most common are Q4_K_M (8 models), Q8_0 (7 models), Q6_K (5 models) and Q2_K (4 models).