AI Agent StoreNVIDIA · Download verified
Nemotron 3.5 Bolt E4B · download
Run a small text assistant locally, including tool calls. A voice assistant still needs separate speech recognition and speech output.
Released 2026-10-23 · First reviewed 2026-10-16 · Checked 2026-10-27.
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 download ID: nvidia/NVIDIA-Nemotron-3.5-Bolt-E4B-4GB. Thinking is enabled by default and can be disabled with enable_thinking. A runtime token budget is not a verified low/medium/high effort menu.
The downloadable GGUF weights use OpenMDW 1.1. Check the license and your runtime’s memory requirements. Publisher speed and quality claims are not independent measurements here.
The model card documents 65,536 tokens shared by input and output. A 4GB weight target does not guarantee that a full-length request fits in 4GB of total memory.
No hosted rate is verified.
Provider release and specifications ↗
Check availability and plans ↗
More setup and licensing details ↗
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 ↗