WTF Is Going On(Weights, Tools & Frameworks)

한국어
ibm-granite/granite-4.2-3b
text-generation apache-2.0 GGUFMLXFP8NVFP4

What this is

3.7B parameters. Writes text from a prompt. This is the kind of model people mean by "an LLM".

Packaged as GGUF, MLX, NVFP4, FP8, the usual download about 2.2 GB. llama.cpp, Ollama and LM Studio read GGUF.

apache-2.0 — commercial use allowed.

Release chainonly the steps this archive can prove

  1. weights posted2026-08-07

Measured herefrom our own daily capture — upstream publishes today only

Who republished itderivatives we have seen, by download size

← the board