GGUF models by ibm-granite
48 GGUF models quantized by ibm-granite on Hugging Face. Sizes run from 164M to 33.7B parameters. The longest trained context is 1024K tokens.
About ibm-granite on Hugging Face
ibm-granite has published 48 GGUF models that ggufmodels.com tracks, across families such as Granite. The most downloaded are Granite 4.2 3b, Granite 4.2 8b and Granite 4.2 30b.
The quants ibm-granite publishes most often are Q4_K_M (47), Q8_0 (39), Q6_K (39) and Q5_K_M (39). Their Q4_K_M files range from 0.2 to 21.4 GB. Parameter counts run from 164M to 33.7B, and the longest trained context window is 1024K tokens.
Frequently asked questions
What GGUF models has ibm-granite published?
48 models are listed here, mainly from the Granite families. The most downloaded is Granite 4.2 3b.
Which quants does ibm-granite publish?
The most common are Q4_K_M (47 models), Q8_0 (39 models), Q6_K (39 models) and Q5_K_M (39 models).