OpenModelsHQ

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16

NVIDIAVisionDenseCustom license

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 is an open-weight vision and language model from NVIDIA with 124B parameters. At 4-bit it needs about 88.7 GB of memory, so the smallest current device that fits it is the DGX Spark.

Overview

Estimated memory at 4-bit
88.7GB

Includes room for an 8k context and runtime overhead. More context needs more memory.

Total parameters
124B
Dense
Context window
Unknown
Not in the model config
Cheapest API, blended / 1M
$0.1325
₹12 · Darkbloom · 3:1 input to output
All NVIDIA API prices

Key information

Lab
NVIDIA
Released
12 Oct 2026
Parameters
124B
Type
Vision and language
Context
Unknown
HF downloads, 30 days
80,269
View all

Will it run on your hardware?

How we estimate
Memory needed vs devices
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 needs about 88.7 GB at 4-bit, 156.7 GB at 8-bit and 295.7 GB at 16-bit. At 4-bit it fits DGX Spark, Mac Studio M5 Ultra (256GB). Dashed lines are usable memory on each device; a model fits when its estimate stays within 90% of it. Log scale. 8k context.
Memory needed vs devices: data
Estimate or deviceMemory
Q488.7 GB
Q8156.7 GB
BF16295.7 GB
RTX 5060 Ti 16 GB16 GB usable
RTX 5090 32 GB32 GB usable
DGX Spark 128 GB108.8 GB usable
Mac Studio M5 Ultra 256 GB192 GB usable

Single-device memory estimate. Pick a device to update the On your device column.

36 GB usable memory

FormatMemory neededOn your deviceExample hardware
4-bit (Q4)≈ 88.7 GBToo big 246%DGX Spark128 GB memory
8-bit (Q8)≈ 156.7 GBToo big 435%Mac Studio M5 Ultra (256GB)256 GB memory
16-bit (BF16)≈ 295.7 GBToo big 821%Mac Studio M3 Ultra (512GB)Discontinued512 GB memory

Fits means the estimate stays within 90% of usable memory. Tight is above 90% and up to 100%. Too big is above 100%. These are memory checks, not speed or compatibility tests.

Mac allowances are 66% of total RAM up to 36 GB, and 75% above. AI boxes allow 85% because their memory is shared with the operating system.

Where to run it

On a Mac

No trusted MLX build found yet.

Check your Mac

With GGUF

No trusted GGUF build found yet.

Find compatible hardware

Through an API

Darkbloom (nvfp4) is the cheapest provider we found.

$0.06 / $0.35

Input / output per 1M tokens
₹5.66 / ₹33 at ₹94.29 per $1

Blended: $0.1325 (₹12) per 1M. Ranked by a 3:1 mix of input and output tokens.

Hosted API 10

USD and INR per million tokensAll NVIDIA API prices
Precision
DarkbloomCheapest$0.1325₹12$0.06₹5.66$0.35₹33262,144NVFP4
Io Net$0.1425₹13$0.09₹8.49$0.30₹28262,144NVFP4
Crusoe$0.175₹17$0.10₹9.43$0.40₹381,048,576BF16
CoreWeave$0.23₹22$0.15₹14$0.47₹441,048,576NVFP4
DeepInfra$0.2375₹22$0.15₹14$0.50₹47262,144FP4
PrimeIntellect$0.2375₹22$0.15₹14$0.50₹471,048,576NVFP4
Together$0.2375₹22$0.15₹14$0.50₹47262,144Not listed
BaseTen$0.275₹26$0.20₹19$0.50₹471,048,576FP4
Venice$0.275₹26$0.20₹19$0.50₹47262,144FP4
Nebius$0.45₹42$0.30₹28$0.90₹851,048,576FP4
View on OpenRouterEndpoint sourceSorted by the blended price: 3 parts input to 1 part output. Context limits differ by provider.

INR at ₹94.29 per $1. Prices fetched 14 Nov 2026.

More about this model

Frequently asked questions

How much memory does NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 need? At an 8k context, about 88.7 GB at 4-bit, 156.7 GB at 8-bit and 295.7 GB at 16-bit (BF16). A longer context needs more.

Can I run NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16 on a Mac? The smallest current Mac that fits the 4-bit estimate of 88.7 GB is the Mac Studio M5 Ultra (256GB). We have not found a trusted MLX or GGUF build yet.

Does the full context fit? We do not have a context length for this model. Our memory estimates use 8k, so long prompts need more memory than shown.

What does it cost through an API? The cheapest provider we found is Darkbloom, at $0.06 per 1M input tokens and $0.35 per 1M output tokens (₹5.66 and ₹33 at 94.29 rupees per dollar). Ranked by a 3:1 mix of input and output tokens.

License in plain English

Custom license. This model uses a custom license rather than a standard one. Read it on the model card before using the model commercially. This summary is not legal advice.

Read the license on the model card

OMHQ RigBench

Not yet tested. We show no speed or quality score without a measurement.

Revision history and sources

Last updated . Sources:Hugging Face model card, OpenRouter.