Local agentic CLI tuned for gemma4:12b-it on CPU-only hardware.
-
Updated
Jul 19, 2026 - Python
#
gemma4-12b
Here are 6 public repositories matching this topic...
A C++23 module-based DNN library for GPU-first LLM inference — explicit forward passes, no hidden execution engine, work at the metal. Validated token-for-token on Gemma 4 Unified, Llama 3.x and GPT-2 with compile-time FP8/FP4 weight quantization.
training deep-learning neural-network gpu cuda transformers inference mnist tensors inference-server gpt-2 cpp23 cpp20-modules llm local-ai llama3-2 flashattention fp8-quantization fp4-quantization gemma4-12b
-
Updated
Jul 20, 2026 - C++
Local image intelligence CLI powered by gemma4:12b via Ollama.
-
Updated
Jun 7, 2026 - Go
Gemma4-12B multimodal specialist on DGX Spark: image input, voice-note workflows, tool calling, 196K tested context.
speech-to-text agents faster-whisper vllms local-ai-agents dgx-spark telegram-bot-ai-assistant hermes-agent multimodal-ai-agents nemoclaw openshell gemma4-12b
-
Updated
Jul 8, 2026 - Python
A dashboard engine that considers every probability. AI only cites, explains, and researches — it never alters a number. Every forecast is finalized before the game begins and evaluated after the full time.
-
Updated
Jul 20, 2026 - Python
Enclave Local is a fully offline, air-gapped AI synthesis platform for generating production-ready codebases and native PowerPoint presentations without cloud API connections.
-
Updated
Jul 13, 2026
Improve this page
Add a description, image, and links to the gemma4-12b topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the gemma4-12b topic, visit your repo's landing page and select "manage topics."