GGUF models by jc-builds
35 GGUF models quantized by jc-builds on Hugging Face. Sizes run from 135M to 26.9B parameters. The longest trained context is 256K tokens.
About jc-builds on Hugging Face
jc-builds has published 35 GGUF models that ggufmodels.com tracks, across families such as Qwen, SmolLM and Phi. The most downloaded are Qwen3.5-9B, Qwen3.5-9B and SmolLM2 135M Instruct Q4 K M.
The quants jc-builds publishes most often are Q4_K_M (31), Q8_0 (5), Q5_K_M (3) and Q4_K_S (2). Their Q4_K_M files range from 0.1 to 16.5 GB. Parameter counts run from 135M to 26.9B, and the longest trained context window is 256K tokens.
Frequently asked questions
What GGUF models has jc-builds published?
35 models are listed here, mainly from the Qwen, SmolLM and Phi families. The most downloaded is Qwen3.5-9B.
Which quants does jc-builds publish?
The most common are Q4_K_M (31 models), Q8_0 (5 models), Q5_K_M (3 models) and Q4_K_S (2 models).