🤖FFPA: Extends FlashAttention-2 via Split-D for large headdims, 1.5x~3×↑🎉 vs SDPA, up to 430T🎉 on H200.
-
Updated
Jun 12, 2026 - Python
#
gemma-4
Here are 89 public repositories matching this topic...
Gemma 4 Agent Skills
ai skills gemini gemma ai-skills gemma-4 ai-edge gemma-skills gemma4-skills gemma-skills-hub gemma4-agent-skills gemma-agent-skills
-
Updated
Apr 7, 2026 - HTML
Autonomous AI Agent Skill for Google AI Edge Gallery - self-evolving, 100% offline
-
Updated
Apr 26, 2026 - JavaScript
The first native Swift inference engine for Gemma 4 on Apple Silicon / iOS
-
Updated
May 1, 2026 - Swift
Reproducible recipe: serve abliterated Gemma-4-12B (gemma4_unified) at 50-118 tok/s on no-NVLink Blackwell (SM120) via vLLM nightly + ModelOpt FP8/NVFP4 + MTP spec-decode.
quantization gemma blackwell fp8 vllm speculative-decoding sm120 nvfp4 abliterated gemma-4 modelopt tensor-parallel
-
Updated
Jun 7, 2026 - Python
Run Gemma 4 locally with Gemma-4 Omni-Desktop. A free, offline AI agent optimized for RTX 30xx & 8GB Macs. Features native vision, voice & OpenClaw support.
-
Updated
Apr 2, 2026 - Go
Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via MLX.
open-source gemma mlx uncensored google-deepmind apple-silicon llm vision-language-model abliteration abliterated gemma-4 guardrail-removal
-
Updated
Apr 3, 2026 - Python
PDF redaction that runs entirely on your device. Five detection layers including Gemma 4 contextual PHI. No uploads, no servers, no leaks.
react open-source pdf redaction privacy typescript ai gdpr pii on-device privacy-first on-device-ai healthcare-ai pdf-redaction ollama hipaa-compliance browser-ai phi-redaction gemma-4
-
Updated
May 18, 2026 - TypeScript
Domain-specialized Gemma 2 27B + Gemma 4 31B for SEC filings — fine-tuned on TPU v6e-8 with PyTorch/XLA FSDPv2, plus a Vertex AI Vector Search RAG demo (69 tickers × 381 filings). Same LoRA recipe, +3.5% / +5.8% BERTScore F1.
finance lora knowledge-distillation gemma tpu peft sec-filings rag streamlit pytorch-xla vertex-ai bertscore gemma-2 gemma-4
-
Updated
Apr 26, 2026 - Python
Run Google's Gemma 4 entirely in your browser via WebGPU. Multimodal chat, E2B vs E4B arena, ONNX conversion toolkit.
react typescript gemma webgpu ai-demo onnx multimodal on-device-ai llm transformers-js browser-ai gemma-4
-
Updated
Apr 9, 2026 - TypeScript
On-device LLM client for Android. Fork of Google AI Edge Gallery
android kotlin privacy gemma multimodal jetpack-compose on-device-ai llm local-llm offline-ai on-device-inference litert-lm gemma-4
-
Updated
May 17, 2026 - Kotlin
HarmonyOS NEXT native Gemma 4 MNN on-device LLM chat demo
napi mnn huggingface on-device-ai harmonyos mobile-ai openharmony llm arkts local-llm harmonyos-next gemma-4 gemma4
-
Updated
May 9, 2026 - C++
Using Google' Gemma 4 Open weights for predicting and analyzing dermatology images, diagnosis and medication
-
Updated
May 23, 2026 - Python
Ash — offline survival assistant for iOS. Gemma 4 E2B/E4B fully on-device (text · image · voice) with RAG-grounded answers over 56 emergency-response packs. Built for the Kaggle Gemma 4 Good Hackathon.
ios offline-first survival flutter gemma emergency-response objectbox litert rag hnsw on-device-ai minilm speculative-decoding on-device-llm litert-lm gemma-4
-
Updated
Jun 10, 2026 - Dart
Offline subtitle translator with 2026 LLMs (Gemma 4, Qwen 3.5, Hunyuan-MT, Llama 4 Scout) via Ollama. Web UI + CLI, 17 languages, video subtitle extraction, persistent Translation Memory, LLM-as-judge quality estimation, genre-aware prompts. No API keys, no cloud.
python docker flask translation ai ffmpeg offline self-hosted subtitles srt gemma translation-memory llm subtitle-translator local-llm ollama qwen gemma-4
-
Updated
Apr 19, 2026 - Python
Distributed systems for automated proposal generation. Orchestrates LLM agents for requirement extraction, semantic inventory matching, and competitive pricing analysis
react workflow distributed-systems fastify rabbit-mq rag vector-search serpapi langchain langgraph agentic-ai gemma-4
-
Updated
Apr 6, 2026 - TypeScript
An exploration or the contradictions of Google Family of LLMs
-
Updated
Jun 16, 2026 - HTML
AI-powered offline health assistant built with React Native. On-device Gemma 4 4B via llama.rn for private, internet-free medical Q&A. Multi-agent AI (drug info, first aid, symptom triage, nearby doctors). Firebase sync, biometric auth, medication insights.
firebase react-native ai healthcare gemma healthcare-application healthcare-ai generative-ai gemma-4 gemma4
-
Updated
May 18, 2026 - TypeScript
Use vision-language models to perform alignment and registration of histological brain sections to any BrainGlobe atlas in any orientation plane.
neuroscience image-registration gemma histology tauri brain-atlas vision-language-model brainglobe gemma-4
-
Updated
Jun 3, 2026 - Python
Improve this page
Add a description, image, and links to the gemma-4 topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gemma-4 topic, visit your repo's landing page and select "manage topics."