All tasks / Models
Nemotron 3.5 Bolt 74B-A9B
NVIDIA's open-weights 74B-total, 9B-active Nemotron derived from Super VL, with an official 24 GB build.
- NVIDIA
- Open weights
- Released 9 Oct 2026
Where it ranks
- CChat & assistantsModels · Local · 21 on Artificial Analysis Intelligence Index (secondary benchmark)
- CCodingModels · Local · 21 on Artificial Analysis Intelligence Index (secondary benchmark)
- –Image understandingModels · Local · no result on this task’s benchmarks yet
Facts
- Vendor
- NVIDIA
- Family
- Nemotron Bolt
- Released
- 9 Oct 2026
- Weights
- Open: download and run it yourself
- License
- OpenMDW-1.1
- Parameters
- 75B (9B active)
- GPU memory to run locally
- ~24 GB (NVIDIA publishes a '24GB' variant (nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB, 22.4 B stored params) sized for 24 GB GPUs; plain 4-bit of the full 75 B ≈ 44 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 | 21 | Nemotron 3.5 Bolt 74B-A9BRaw value from the page's embedded model data; the site displays it rounded to an integer. | 19 Oct 2026 | artificialanalysis.ai |
Where you can use it
No tracked tool lists this model yet; as open weights it runs in local runtimes.