bi0
/

NVIDIA_Nemotron-3.5-Rerank-8B-NVFP4

Model card Files Files and versions

NVIDIA_Nemotron-3.5-Rerank-8B-NVFP4

HuggingFace Repository: bi0/NVIDIA_Nemotron-3.5-Rerank-8B-NVFP4 (PUBLIC)
Privacy & Provenance Audit: PUBLIC (Zero Private Data — Pure Hardware NVFP4 + TensorRT 11.3 Compilation)
Upstream Base Model: nvidia/Nemotron-3.5-Rerank-8B-BF16
Optimization / Modification Method: Blackwell NVFP4 (fp4_e2m1 Block-16) + TensorRT 11.3.0.99 Engine (sm_121a)
Format: TensorRT .engine + NVFP4 Safetensors
Local DGX Spark GB10 Path: /home/m1st/ai_workspace/models/NVIDIA_Nemotron-3.5-Rerank-8B-NVFP4/NVIDIA_Nemotron-3.5-Rerank-8B-NVFP4_sm121_GB10.engine
Size: 820.47 MB (860319940 bytes)
Fingerprint (SHA-256): da6259152c8e76c749a39f6ab2a97ae44ff5e852b313e811cd13daa773437058
Last Modified: 2026-11-07 01:03
Active Runtime Port: 8093

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for bi0/NVIDIA_Nemotron-3.5-Rerank-8B-NVFP4

Base model

mistralai/Ministral-3-8B-Base-2512

Finetuned

mistralai/Ministral-3-8B-Instruct-2512-BF16

Finetuned

nvidia/Nemotron-3.5-Rerank-8B-BF16

Finetuned

(2)

this model