llama.cpp fork tuned for running modern models (Gemma-4, Qwen3.x) at full context on 12 GB Turing GPUs (RTX 2060/2070/2080, T4). TurboQuant KV cache (KTQ+VTQ, 2.78 bpw f16-quality), SWA-aware KV, MTP+n-gram speculation.
GitHub repository with 6 stars and 0 forks.
Language: C++
Topics: fine-tuning, kv-cache, llama-cpp, llama-tq, low-vram, speculative-decoding, turboquant, turing
Trending score 0.10, freshness score 1.00, stars gained +0, forks gained +0.
2026-06-15: 6 stars and 0 forks.
llama.cpp fork tuned for running modern models (Gemma-4, Qwen3.x) at full context on 12 GB Turing GPUs (RTX 2060/2070/2080, T4). TurboQuant KV cache (KTQ+VTQ, 2.78 bpw f16-quality), SWA-aware KV, MTP+n-gram speculation.
GitHub repository with 6 stars and 0 forks.
Trending score: 0.10; stars gained: +0; forks gained: +0.
Language: C++
Topics: fine-tuning, kv-cache, llama-cpp, llama-tq, low-vram, speculative-decoding
LLM inference in C/C++
GitHub repository with 116,642 stars and 19,597 forks.
Trending score: 4.92; stars gained: +285; forks gained: +59.
Language: C++
Topics: ggml
Open Source Computer Vision Library
GitHub repository with 89,164 stars and 56,658 forks.
Trending score: 4.35; stars gained: +147; forks gained: +16.
Language: C++
Topics: c-plus-plus, computer-vision, deep-learning, image-processing, opencv
Port of OpenAI's Whisper model in C/C++
GitHub repository with 50,734 stars and 5,664 forks.
Trending score: 3.92; stars gained: +155; forks gained: +26.
Language: C++
A sleek and minimal desktop shell thoughtfully crafted for Wayland.
GitHub repository with 7,757 stars and 544 forks.
Trending score: 3.82; stars gained: +91; forks gained: +10.
Language: C++
Topics: dotfiles, hyprland, linux, niri, noctalia, quickshell
Godot Engine – Multi-platform 2D and 3D game engine
GitHub repository with 112,544 stars and 25,650 forks.
Trending score: 3.67; stars gained: +64; forks gained: +11.
Language: C++
Topics: game-development, game-engine, gamedev, godot, godotengine, multi-platform
Animated sprite editor & pixel art tool (Windows, macOS, Linux)
GitHub repository with 37,501 stars and 8,168 forks.
Trending score: 3.52; stars gained: +64; forks gained: +17.
Language: C++
Topics: animated-sprites, animation, aseprite, c-plus-plus, cpp, draw
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
GitHub repository with 66,565 stars and 5,964 forks.
Trending score: 3.87; stars gained: +76; forks gained: +12.
Language: Python
Topics: agent, deepseek, fine-tuning, gemma, gemma3, gpt-oss
Your Cheat Sheet for AI Engineering Interview – Questions and Answers.
GitHub repository with 1,864 stars and 339 forks.
Trending score: 3.06; stars gained: +32; forks gained: +5.
Language: Markdown
Topics: agents, ai, ai-agents, ai-engineering, fine-tuning, interview
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
GitHub repository with 4,378 stars and 706 forks.
Trending score: 2.90; stars gained: +35; forks gained: +0.
Language: Go
Topics: ai-gateway, bert-classification, fine-tuning, golang, huggingface-candle, huggingface-transformers
Estimate whether a Hugging Face model fits and fine-tunes on your local GPU.
GitHub repository with 495 stars and 71 forks.
Trending score: 2.82; stars gained: +20; forks gained: +2.
Language: Python
Topics: bitsandbytes, fine-tuning, gpu, hugging-face, llm, lora
Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine
GitHub repository with 168 stars and 17 forks.
Trending score: 2.24; stars gained: +18; forks gained: +3.
Language: Python
Topics: audio, cross-lingual, deep-learning, fine-tuning, multi-lingual, python
Go ahead and axolotl questions
GitHub repository with 12,049 stars and 1,368 forks.
Trending score: 2.16; stars gained: +11; forks gained: +1.
Language: Python
Topics: fine-tuning, llm