All tasks / Models
Granite 4.2 30B
IBM's open-weights enterprise Granite LLM line (Apache-2.0); the 30B is the largest of the 4.2 sizes.
- IBM
- Open weights
- Released 7 Aug 2026
Where it ranks
- CChat & assistantsModels · Local · 1,340 on LMArena Text Arena (overall, style control)
- CCodingModels · Local · 13 on Artificial Analysis Intelligence Index (secondary benchmark)
Facts
- Vendor
- IBM
- Family
- Granite
- Released
- 7 Aug 2026
- Weights
- Open: download and run it yourself
- License
- Apache-2.0
- Parameters
- 29.3B
- GPU memory to run locally
- ~18 GB (4-bit ≈ 29.3 B × 0.57 GB + 1.5 GB ≈ 18 GB, estimate.)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Price from huggingface.co, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index | 13 | Granite 4.2 30BRaw value from the page's embedded model data; the site displays it rounded to an integer. | 19 Oct 2026 | artificialanalysis.ai |
| LMArena Text Arena (overall, style control) | 1,340 | granite-4.2-30bFrom LMArena's official leaderboard-dataset (text_style_control, split latest, category overall, published 2026-10-15), which mirrors https://arena.ai/leaderboard/text. Rank 235; 3401 votes; 95% CI 1329.5-1350.5. | 15 Oct 2026 | huggingface.co |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.