Can Desktop PC · GeForce RTX 5060 Ti 16GB · 32 GB RAM run Nemotron 3.5 Super VL 120B-A12B?
16 GB VRAM + 32 GB RAM · 448 GB/s memory bandwidth · Nemotron 3.5 Super VL 120B-A12B has 120B parameters (12B active per token).
Short answer
No. This combination isn't supported.
Nemotron 3.5 Super VL 120B-A12B is not published in a format llama.cpp (llama-server) can load (GGUF).
The same applies to every workload we rate (chat, coding questions, coding in a repository, agentic coding and long documents): they all need at least as much memory as chat.
Other models for Desktop PC · GeForce RTX 5060 Ti 16GB · 32 GB RAM
The best-rated models for chat on this machine.
- gpt-oss-20b≈100 tok/sExcellent
- Gemma 4 26B-A4B120–160 tok/sExcellent
- MiniCPM5 2B110–140 tok/sExcellent
- Qwen3.5 9B35–50 tok/sExcellent
- Qwen3.5 4B65–90 tok/sExcellent
- Gemma 4 12B30–40 tok/sExcellent
Cheapest machines for Nemotron 3.5 Super VL 120B-A12B
Hardware rated comfortable or better for chat, lowest price first.
- Mac Studio M2 Max 96 GB$3,799 · 25–35 tok/sExcellent
- MacBook Pro M3 Max 96 GB$3,999 · 20–30 tok/sExcellent
- Mac Studio M4 Max 128 GB$4,099 · 35–45 tok/sExcellent
- Mac Studio M5 Max 128 GB$4,099 · 30–50 tok/sExcellent
- MacBook Pro M2 Max 96 GB$5,099 · 25–35 tok/sExcellent
- MacBook Pro M4 Max 128 GB$5,299 · 35–45 tok/sExcellent
Different tool, context size or workload?
These pages use typical settings. The full check models your exact setup.