Nemotron 3.5 Super VL 120B (local)
Workstation-class open model for document-heavy agents: OCR, tables, charts and PDFs plus tool calling.
Run it locally
ollama run nemotron-3.5-super- Ollama tag
- nemotron-3.5-super (120b)
- LM Studio name
- nvidia/nemotron-3.5-super-vl
- Download size by quantization
- 80 to 90 GB download (Ollama); LM Studio lists 70 GB minimum memory
- License
- OpenMDW 1.1
Memory needed is roughly the download size plus 2 to 4 GB for context. See how to run AI locally.
Specs and prices checked 2026-10-16 against the official page.
Used in these setups
Related skills and personas
Agent skills and bot personas that pair well with Nemotron 3.5 Super VL 120B (local).
React 19 Best Practices & Performance Skill
Zero unnecessary rerenders, modern hooks, useActionState, and clean server component architecture.
FastAPI & Pydantic v2 Production Rule
Async route handlers, dependency injection, and Pydantic v2 model serialization rules.
Systematic Root-Cause Debugging Skill
Disciplined scientific investigation of software defects without guessing or blind trial-and-error.
Brave Search MCP Server
Fast privacy-focused web search and local index queries without tracking or ad pollution.
The Pragmatic Staff Engineer
High standards, zero bloat, resilient architecture, and concise reasoning.
The Inversion Advisor
Before you commit to a plan, it works out how the plan would fail and helps you avoid those exact mistakes.
Want tested skills and personas installed in one command? See the AI Loadout packs, from $9.