An update to the Granite series by IBM. Alongside a toggle-able reasoning mode, which was previewed as an experiment, it also supports fill-in-the-middle to be used as an in-line coding model.
Specs
Params8B
LicenseApache-2.0
Tags
modelsmodels/llmsmodels/llms/reasoningmultilingualartifacts/9
Capability · Artificial Analysis
AA Index
1.8
RAM score
—
Hugging Face Downloads
97K
last 30d
1.8M
all time
HF Likes
158
Relative Adoption Metric contextualizes downloads against the model's size bucket.
VAIL Fingerprint
003b:0059:0086:00af:00ec:0156:0295:5341
Explore other models with behavioral similarity to granite-3.3-8b-instruct.
Related Models
