Granite 4.2 3B, GGUF

Granite 4.2 3B is a compact reasoning model designed for coding, mathematics, tool calling, agentic workflows, and multilingual dialogue. The architecture employs Grouped Query Attention, with native reasoning and flexible thinking modes for balancing quality and latency. It is optimized for efficient long-context reasoning and enterprise applications.

This repository holds Vultr's GGUF quantizations of it. They are hybrid quantizations: rather than applying one precision to the whole network, each layer's precision is chosen from a measured importance score, so the bits go where they change the output most.

Model Overview

Quantizations

KL divergence measures how far a quantized model's next-token probabilities drift from those of the original bf16 model, averaged over every token of the evaluation text. The lower the value, the closer the quantized model is to the original; zero would mean identical output.

Evaluation

Every variant in this repository was evaluated against the original bf16 model for perplexity, KL divergence, top-token agreement, HellaSwag and WinoGrande, under identical conditions. The full results are maintained on the model's page in the Vultr Model Library:

https://docs.vultr.com/models/ibm-granite-42/granite-4.2-3b?tab=quantized

That page is the reference for these files. The summary above is an excerpt from it.

Run

llama-server -hf vultr/granite-4.2-3b-GGUF:Q4_K_M

The model's chat template is embedded in every file, so no extra prompt formatting is needed.

License

These files are derived from ibm-granite/granite-4.2-3b and are distributed under the same license, Apache 2.0. The model is the work of IBM Granite; Vultr produced the quantizations.