HomeModelsAny To AnyprithivMLmods/gemma-4-E4B-it-NVFP4
G

prithivMLmods/gemma-4-E4B-it-NVFP4

Any To Any·prithivMLmods· 243.4K· 3
transformers apache-2.0 Any To Any 6.9B params base_model:google/gemma-4-E4B-itbase_model:quantized:google/gemma-4-E4B-itlicense:apache-2.0

gemma-4-E4B-it-NVFP4 is an NVFP4-compressed evolution of gemma-4-E4B-it. This variant leverages F32 · BF16 · F8E4M3 · U8 precision formats to significantly reduce memory footprint and improve inference efficiency while maintaining strong output quality. gemma-4-E4B-it from Google is a 4.5B effective parameter (8B total with Per-Layer Embeddings) multimodal dense model in the Gemma 4 family, optimi

Open in MLForge Sign up free Desktop app Source ↗
# pull & run locally
pip install mlforge-sdk && mlforge pull prithivMLmods/gemma-4-E4B-it-NVFP4

Model details

Task
Any To Any
Provider
prithivMLmods
Framework
transformers
Parameters
6.9B
Size
11 GB
License
apache-2.0
Downloads
243.4K
Likes
3
Updated
2026-04-03

About prithivMLmods/gemma-4-E4B-it-NVFP4

gemma-4-E4B-it-NVFP4 is an NVFP4-compressed evolution of gemma-4-E4B-it. This variant leverages F32 · BF16 · F8E4M3 · U8 precision formats to significantly reduce memory footprint and improve inference efficiency while maintaining strong output quality. gemma-4-E4B-it from Google is a 4.5B effective parameter (8B total with Per-Layer Embeddings) multimodal dense model in the Gemma 4 family, optimized for edge deployment on laptops, high-end smartphones, and consumer GPUs with native support for text, images (variable aspect ratio and resolution), audio processing, and configurable thinking modes for step-by-step reasoning. Featuring 42 layers, a 512-token sliding window, 128K context length, and a 262K vocabulary, it delivers frontier-level performance in agentic workflows, multilingual OCR and handwriting recognition, document and PDF parsing, UI and screen analysis, chart interpretation, object detection with pointing, coding assistance, and low-latency speech-to-text understanding. Rivaling models 10 to 20× larger while maintaining Google's production-grade safety alignments, the instruction-tuned variant excels at on-device autonomous agents via Android AICore and Qualcomm optimizations, with open weights enabling local-first inference across MediaTek and ARM CPUs as well as NVIDIA RTX GPUs for privacy-focused applications such as mobile IDEs, real-time document processing, and structured data extraction in resource-constrained environments.

Related Any To Any

G google/gemma-4-E4B-it Any To Any ·8.0B params 6.0M 1.3K 🤗 HF G google/gemma-4-E2B-it Any To Any ·5.1B params 2.3M 777 🤗 HF G google/gemma-4-12B-it Any To Any ·12.0B params 2.2M 1.2K 🤗 HF Q Qwen/Qwen3-Omni-30B-A3B-Instruct Any To Any ·35.3B params 2.0M 944 🤗 HF N nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-NVFP4 Any To Any ·18.3B params 1.7M 145 🤗 HF G google/gemma-4-12B-it-qat-w4a16-ct Any To Any ·13.3B params 1.7M 33 🤗 HF

Browse all Any To Any models →