AI Agent StoreNVIDIA · Provider documented
Nemotron 3.5 Bolt 74B · 24GB
Run text and visual tasks on your own hardware with NVIDIA’s compressed 74B model. The 24GB package reduces the weight footprint; working memory and a compatible serving setup are still needed.
Released 2026-10-15 · First reviewed 2026-10-16 · Checked 2026-11-03.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Try it on your hardware and tasks before relying on it.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact checkpoint ID: nvidia/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-24GB. Thinking can be switched on or off. No matched independent comparison of these modes is available here.
OpenMDW 1.1 weights. Follow the provider’s supported GPU and software recipe; the package size is not a guarantee that the full context fits on every 24GB device.
The card supports up to 262,144 combined tokens. Prompts, images, video, history and generated text share the space; serving recipes can set smaller limits.
This is a download, not a verified hosted token offer. Include hardware, memory and operation in your budget.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗