minkyoungs/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-IA-REAP-40-PIE

AI model by minkyoungs

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4 with 40% of the routed experts removed by non-uniform expert pruning (IA-REAP (instruction-aware REAP)). layers (layers 1, 3, 85, 87) keep all 512) Experts are scored with REAP on Korean and English calibration data (the larger of the two normalized scores is kept per expert). Within each layer, the score is then adjusted by how much an expert's routing share rises when a same-language system prompt ("Respond in the same language as the user's message ...") is present, so experts used for following the user's language are kept preferentially. The number of experts removed per layer is set from the unadjusted scores. The number of experts per layer is non-uniform: MoE layers are grouped into 4 clusters by their mean expert score, every cluster removes the same share, and inside a cluster experts are removed 8 at a time from the layer whose next 8 lowest-scored experts have the…

minkyoungs/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-IA-REAP-40-PIE on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-11-10T08:25:26.928Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: other. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

minkyoungs/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4-IA-REAP-40-PIE is a task-unspecified model repository published by minkyoungs on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: Not reported
Library: Not reported
Recent downloads (30 days): 0
Cumulative likes: 0
Hugging Face trending score: 0
Reported safetensors parameters: 43,187,699,210
Architecture: NemotronH_Omni_Reasoning_V3
License: other
Access: Not gated by Hugging Face
Created: 2026-11-10T06:40:54.000Z
Last modified: 2026-11-10T06:43:54.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-11-10T06:56:23.256Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source