Local LLM inference engine written from scratch in Rust — hand-written AVX-512 assembly kernels, Metal & Vulkan compute shaders. Supports Qwen3, Mistral3, ... Q4/INT8/BF16 quantization.
-
Updated
Mar 18, 2026 - Rust
#
gemma
Here are 14 public repositories matching this topic...
Real-time LLM interp framework in Rust
rust machine-learning gem rust-lang inference-server gemma sparse-autoencoder llm mechanistic-interpretability gemma-2b
-
Updated
Mar 17, 2026 - Rust
rust api wrapper for llm-inference chatllm.cpp
rust chatbot inference bindings api-wrapper llama quantization gemma mistral cpu-inference llm llms chatllm ggml llm-inference qwen
-
Updated
Nov 27, 2024 - Rust
Rust-native AI inference & training engine. Block AttnRes linear-time transformer with profile-driven GPU dispatch, TurboQuant, GGUF/SafeTensors, LoRA, multimodal (vision/audio/video), FerrisRes Armor security. 39K LOC, 951 tests. Adapts to any GPU via wgpu — Intel iGPU to H100. No Python.
training rust sandbox vulkan wasm inference transformer lora gemma distillation multimodal rag wgpu self-improving linear-attention llm safetensors agentic concept-memory block-attention
-
Updated
Apr 23, 2026 - Rust
Gemma 4 on a 24GB MacBook: measured recipes, runtimes, and fallback paths.
macos benchmarking machine-learning inference language-model gemma mlx karpathy apple-silicon llm local-llm local-ai gguf localllama m4-pro autoresearch gemma-4
-
Updated
Apr 24, 2026 - Rust
Offline multimodal evidence capture that emits a signed, locally verifiable .witness bundle. Tauri + Rust + Gemma 4 + Ed25519. Static HTML verifier runs with no server.
rust offline-first verification provenance civic-tech ed25519 gemma evidence tauri tamper-evident multimodal-ai signed-evidence
-
Updated
May 17, 2026 - Rust
Local-first AI document intelligence for CPA firms. Extracts W-2s, 1099s, and financial statements on-device — no data leaves your machine.
react desktop-app rust pdf privacy typescript sqlite gemma cpa tauri document-extraction llm local-ai ollama
-
Updated
May 6, 2026 - Rust
🖥️ Explore CPU-SLM, a Rust-based SLM/LLM project that runs on CPU, offering efficient inference and chat with minimal dependencies.
nlp rust machine-learning transformers simd avx2 llama slm quantization gemma mistral fine-tuning cli-tools local-first llm llama-cpp qlora qwen gguf unsloth
-
Updated
May 21, 2026 - Rust
Translate EPUB files using Gemma
macos rust translator ai objective-c ebook epub translate appkit gemma epub-translator ebook-translator llamacpp translategemma llama-cpp-2
-
Updated
Apr 6, 2026 - Rust
Free, local-first AI dictation for macOS and Windows. Auditable, offline-first, privacy by design. [Pre-PoC]
windows macos rust privacy typescript cross-platform offline-first japanese speech-to-text dictation whisper gemma tauri voice-input tauri-app onnx-runtime local-llm phi-4 whisperkit
-
Updated
May 18, 2026 - Rust
Improve this page
Add a description, image, and links to the gemma topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gemma topic, visit your repo's landing page and select "manage topics."