Nemotron 3.5 Super VL arrives on Ollama with 5x throughput
NVIDIA's Nemotron 3.5 Super VL is now on Ollama, featuring a hybrid Mamba-2/Transformer architecture with 120B total parameters (12B active), 1M-token context, and 5x single-GPU throughput for agent workloads.
2026-10-16 ~ 2026-10-16 · 2 related posts
- Episode 1: NVIDIA Releases Nemotron 3.5: Super 120B and Lightning 30B(2026-10-15, 6 posts)
- Episode 2: NVIDIA Open-Sources Nemotron 3.5 Super VL and Bolt Model Family(2026-10-15, 35 posts)
- Episode 3: NVIDIA Nemotron 3.5 Super VL tops US open-weight models(2026-10-15, 2 posts)
- Episode 4: NVIDIA Launches Nemotron 3.5 Bolt: 74B Model in 24GB VRAM(2026-10-16, 2 posts)
- Episode 5: Nemotron 3.5 Super VL arrives on Ollama with 5x throughput(2026-10-16, 2 posts)
- Episode 6: NVIDIA Nemotron 3.5 Bolt lands on Ollama(2026-10-16, 2 posts)
- NVIDIA's Nemotron 3.5 Super VL lands on Ollama with up to 5x single-GPU agent throughput — ollama · 2026-10-16
- Nemotron 3.5 Super: 120B params, 12B active, Mamba-2 hybrid MoE with 1M context — ollama · 2026-10-16