Model Library/Nemotron 3.5 Super VL

NVIDIA

Nemotron 3.5 Super VL

A vision-language MoE for text, images and short video. 75 GB at NVFP4.

MultimodalTextvLLMllama.cpp2 builds

Recommended: DGX Spark, 128 GB unified, $0.79 / hour, billed per minute. Check availability.

Configure

Every build below is published on Hugging Face and fits at least one GPU we rent. Pick the quantization and engine: the memory it needs, the GPUs it fits and the recommended GPU follow, and Deploy takes that exact build, revision and GPU to the console. Only the one-click preset is tested by GPUwerk.

Nemotron 3.5 Super VL, NVFP4 on vLLM
QuantizationNVFP4
EnginevLLM
StatusRun it yourself: needs the model's own code
Weights75 GB
GPU memory it needsAbout 89.2 GB with a 32k-token cache, an estimate
Recommended GPUDGX Spark, $0.79 / hour
Weights sourcenvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4, revision ae1368329b1f
Licence on the cardother
GPUs Nemotron 3.5 Super VL NVFP4 does and does not fit
GPUMemoryPriceAvailabilityDeploy
RTX 5090x86 · Blackwell32 GB GDDR7Does not fit: needs about 89 GB of GPU memory (weights 75.0 GB plus cache, an estimate); RTX 5090 offers 29 GB to it.
DGX SparkArm · GB10 · recommended128 GB unified$0.79 / hourCheck availabilityRun it yourself Nemotron 3.5 Super VL NVFP4 on DGX Spark
RTX PRO 6000x86 · Blackwell96 GB GDDR7Does not fit: needs about 89 GB of GPU memory (weights 75.0 GB plus cache, an estimate); RTX PRO 6000 offers 86 GB to it.
H100 SXMx86 · Hopper80 GB HBM3Does not fit: NVFP4 weights need a Blackwell GPU; H100 is not one.
H200x86 · Hopper141 GB HBM3eDoes not fit: NVFP4 weights need a Blackwell GPU; H200 is not one.
B200x86 · Blackwell180 GB HBM3e$5.49 / hourCheck availabilityRun it yourself Nemotron 3.5 Super VL NVFP4 on B200
B300x86 · Blackwell288 GB HBM3e$6.49 / hourCheck availabilityRun it yourself Nemotron 3.5 Super VL NVFP4 on B300

Builds by the model's maker, NVIDIA and Unsloth, read from Hugging Face on 21 November 2026. Memory is an estimate (weights x 1.15 plus 3 GB); GGUF runs on llama.cpp, which GPUwerk builds for the DGX Spark only, and NVFP4 needs a Blackwell GPU. SGLang is not offered: there is no SGLang runtime yet.

Details

About the model.

Nemotron 3.5 Super VL
MakerNVIDIA
TaskMultimodal · Text
Parameters120B total, 12B active (mixture of experts)
LicenceOpenMDW-1.1

No speed figure here: GPUwerk lists only figures it measured itself. Reported figures, with their sources, are in the model guide.

Quick start

  1. Deploy a DGX Spark with a base image (DGX OS or Ubuntu).
  2. Follow the Nemotron 3.5 Super VL guide to download the weights and start vLLM.
  3. Connect over SSH or the browser terminal; the machine is yours until you terminate it.

SSH, the browser terminal, VNC and your workspace work the same on every instance. Terminate when you are done and billing ends.

Related models

QwenCoding · Text

Qwen3 Coder 30B

A coding model for agents and editors, with tool calls turned on.

One-click preset · vLLM · RTX 5090

QwenText

Qwen3.6 35B-A3B

A fast mixture-of-experts model for chat and agents, also on the pay-per-token API.

One-click preset · llama.cpp · DGX Spark

OpenAIText

GPT-OSS 120B

OpenAI's open-weight 120B model, quantized to fit one DGX Spark.

One-click preset · llama.cpp · DGX Spark

All models in the library