SSyncDev

Nemotron 3.5 Super VL 120B A12B

SyncDev model directory · Profile updated Nov 17, 2026

Compare with another model

Nemotron 3.5 Super VL 120B A12B is NVIDIA's open multimodal reasoning MoE: 12B active, 1M context, image and video input, switchable thinking.

Key specifications

Specification score
66.7
Context window
1.05M
Input / 1M tokens
From $0.15
Output / 1M tokens
From $0.50
License
OpenMDW-1.1

The specification score summarizes recorded features and limits. It is not a benchmark result.

Pricing conditions: Weights free (OpenMDW-1.1). Indicative hosted price on OpenRouter: $0.15 input / $0.50 output per 1M tokens, plus a free tier. Confirm on your own account.

Inputs and outputs

Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.

Accepts

  • Text input
  • Image input
  • Video input

Produces

  • Text output

Capabilities

ReasoningFunction callingVisionOpen weights

What is Nemotron 3.5 Super VL 120B A12B?

Four H100s or two GB200s. That is NVIDIA's reference footprint for serving Nemotron 3.5 Super VL 120B A12B in full BF16 precision, and it tells you who this model is for: teams that want a frontier-class open reasoning model they can host themselves, with vision and video built in rather than bolted on.

Released on 15 October 2026 under the OpenMDW-1.1 licence, it succeeds the text-only Nemotron 3 Super 120B A12B.

Architecture in brief

It is a hybrid Mamba-2 and Transformer mixture-of-experts with 120B total and 12B active parameters, 512 routed experts per MoE layer, multi-token prediction, and a C-RADIO vision encoder. Pretraining covered about 26 trillion tokens, and NVIDIA released open datasets and recipes alongside the weights.

The multi-token prediction head doubles as a built-in drafter for speculative decoding, so no separate draft model is needed.

Spec sheet

Item Detail
Model ID nvidia/nemotron-3.5-super-vl-120b-a12b
Weights nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16; NVFP4 build also published
Parameters 120B total / 12B active
Context Up to 1M tokens
Input Text, JPEG/PNG images, MP4 video up to 2 minutes
Output Text
Reasoning Off, medium effort, or full
Licence OpenMDW-1.1
Indicative hosted price $0.15 in / $0.50 out per 1M tokens (OpenRouter); free tier offered

Thinking, three ways

Reasoning is controlled from the chat template: enable_thinking true or false, and medium_effort for a middle setting that spends fewer tokens at some cost to accuracy. Reasoning and final-answer tokens share the max_tokens budget, so set it generously when thinking is on.

Publisher-reported scores

NVIDIA reports GPQA-Diamond 89.5, SWE-bench Verified 71.1, LiveCodeBench v6 88.2, MathVision 78.2 and OSWorld-Verified 51.1. Treat them as a shortlist reason, not a verdict.

Inconsistencies to resolve yourself

  • Languages. NVIDIA's metadata says six languages; its training notes cite English plus 19 others. Test the languages you need.
  • Max output. One listing gives 8,192 output tokens; OpenRouter allows a maximum completion of 235,929. Check the limit on whichever endpoint you call.
  • Sampling. The summary recommends temperature 0.6 for vision; the vision examples use 1.0. Try both.
  • A "text-only" listing. Some catalogues carry a text-only nemotron-3.5-super-120b-a12b. NVIDIA publishes only the VL checkpoints, so treat that as this model.

Sizing a pilot

Start on a hosted endpoint (NIM on build.nvidia.com, OpenRouter, or ModelScope) before buying GPUs. Run your agent traces with thinking off, medium and full, and log tokens per task as well as success rate; medium often wins on cost. If you self-host, vLLM and SGLang have documented recipes, and the NVFP4 build targets Blackwell. Compare against Qwen3.5 122B-A10B, a similar-sized open MoE.

More from NVIDIA on its provider page, and peers under image-text-to-text. Hosted prices are indicative; confirm on your account.

How to evaluate Nemotron 3.5 Super VL 120B A12B

Compare the model on the work you need to complete.

Tasks and inputs

Nemotron 3.5 Super VL 120B A12B is listed for Image-text-to-text, Text generation, Video-text-to-text, Coding & Code Generation. It accepts text, image, video and produces text. Use the publisher’s input format and preprocessing for your chosen deployment.

Capacity and cost

Documented limits: 1.05M context. The listed route has starting rates of $0.15 input and $0.50 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.

Choosing a deployment

The weights are downloadable under OpenMDW-1.1. Check runtime support and size the complete model and working context for your expected concurrency.

Frequently asked questions

12B of 120B total, in a hybrid Mamba-2/Transformer mixture-of-experts with 512 routed experts per MoE layer.

These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.

sensetime

SenseNova-Loop-9B

SenseNova-Loop-9B is SenseTime's 9B looped multimodal model: 32 layers run as 56, 512K context, ~15 GiB at 256K in 4-bit, open weights under Apache 2.0.

524.29K context

Tencent

Hy4 Flash

Tencent Hy4 Flash is the low-cost Hy4 tier with open weights: a 220B MoE (~11.3B active) for agents and documents, with 1M context and image input.

1.05M context

shanghai-ai-lab

Sage S2.1 Flash

Sage S2.1 Flash is Shanghai AI Lab's open scientific multimodal agent model, reading molecules, crystals and proteins alongside text and images.

— context

Meituan

LongCat-2.5

LongCat-2.5 is Meituan's open-weight MIT-licensed multimodal MoE for long-horizon agents: screenshots, charts, video and multi-step coding.

— context

sensetime

SenseNova-Loop-9B-Preview

SenseNova-Loop-9B-Preview is SenseTime's looped 9B text-and-image model for long-context agentic work, running shared layers twice for extra depth.

262.14K context

Liquid AI

LFM3-VL-2B

LFM3-VL-2B is Liquid AI's open 2B vision-language model for images and video on-device, strong on documents, charts and GUI screenshots.

— context