gemma-4-12b-nvfp4

HuggingFace Repository: bi0/gemma-4-12b-nvfp4 (PUBLIC)
Privacy & Provenance Audit: PUBLIC (Zero Private Data — Pure Blackwell NVFP4 Quantization)
Upstream Base Model: google/gemma-4-12b-it
Optimization / Modification Method: Blackwell NVFP4 Block-16 Quantization
Format: NVFP4 Safetensors
Local DGX Spark GB10 Path: /home/m1st/ai_workspace/models/gemma-4-12b-nvfp4
Size: 11198.61 MB (11742594491 bytes)
Fingerprint (SHA-256): c9200baf51f656bfe66f57e4e13440bb9e5de4693f949b0a62a2e9b958d6471b
Last Modified: 2026-06-13 06:05
Active Runtime Port: On-Demand / Adapter

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

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