Llama-3.1-Nemotron-Nano-VL-8B-V1

AI model

Context window: 16,384 tokens
Open weights: Yes

No matched benchmark results are available for this entry yet.

Run it locally

Inference · memory estimate

Llama-3.1-Nemotron-Nano-VL-8B-V1

16.2 GiB checkpoint tensor payload · 8.72 B stored tensor elements · BF16

Stored tensors can include buffers and repeated shared weights. A verified unique parameter count is unavailable. Checkpoint size is not the memory required to run the model.

Capabilities

Context window: 16,384 tokens
Open weights: Yes
Model license: other
Checkpoint tensor payload: 16.25 GiB

Input modalities

text
image

Output modalities

text

Processing & platform

Architecture: Llama_Nemotron_Nano_VL

Connectivity & software

Connectivity & features

Language-backbone position capacity: 131,072 tokens; the full model lists a 16,384-token input/output window.