IBM has (rather quietly) released updates to its Granite series by continuing post-training on its 3B dense, 8B dense, and 30B dense models. In terms of raw performance, however, these models are behind the likes of Qwen and Gemma.
Specs
Params30B
LicenseApache-2.0
Similarity · VAIL
VAIL Fingerprint
025e:0346:046e:06c4:0945:12e8:1bf0:625f
Explore other models with behavioral similarity to Granite-4.1-30B.
Capability · Artificial Analysis
AA Index
8.7
Months Behind Frontier
24+ mo
claude-3-opus
04 Mar 2024
Adoption · Hugging Face
RAM @ 30d
Relative Adoption Metric: 0.02×. Below benchmark. Measured at 30 days.
Hugging Face Downloads
24.9K
last 30d
154.8K
all time
HF Likes
145
Relative Adoption Metric contextualizes downloads against the model's size bucket.
Related Models
