NVLM D 72B is an open-source multimodal chat model from NVIDIA that accepts text and image inputs and returns text outputs. It is designed for vision-language tasks such as optical character recognition, multimodal reasoning, and coding from visual inputs.
Input
Output
Context
128K
Max Output
-
Parameters
79.4B
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
| Precision | Weights | One request at 33K tokens | Smallest GPU that fits |
|---|---|---|---|
| FP16 / BF16 | 148 GB | 164 GB | 1x NVIDIA B200 SXM (192 GB) |
| INT8 | 73.9 GB | 86.5 GB | 1x AMD Instinct MI250X (128 GB) |
| INT4 | 37.0 GB | 47.6 GB | 1x Biren BR100 (64 GB) |
Computed by Inferbase from the 79,379,593,344 parameters in the creator's Hugging Face repository; one request adds its KV cache, activations and framework overhead, with the layer layout estimated from the parameter count.
Public resources
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
NVLM D 72B has a context window of 128,000 tokens (source: Web research). A provider may serve less; Inferbase routes on what each provider serves.
Yes. NVLM D 72B is an open-weight model under the Cc by nc 4.0 license. You can download and self-host it within the license terms.
NVLM D 72B has 79,379,593,344 parameters (79.4B), as stated in the creator's Hugging Face repository.
Limitations: License does not allow commercial use (cc-by-nc-4.0). Each is computed from the model's stated facts and benchmark results.
NVLM D 72B accepts Text and Image and produces Text. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for NVLM D 72B yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves NVLM D 72B, and Inferbase runs it on your account with the same routing and logs.
The weights take 147.9 GB at FP16 / BF16, 73.9 GB at INT8, 37.0 GB at INT4, computed from the 79,379,593,344 parameters its creator publishes. Each request adds its KV cache and the framework's overhead. The hardware section shows one request and the smallest GPU that fits; the GPU planner sizes it for your context length and traffic.
The model card of NVLM D 72B lists one language: English. That is what NVIDIA states; the catalog does not test language quality.
Start on the free plan with 5,000 requests a month, no card required.