CPU LM Speed Leaderboard
Benchmark any LM <1B params on CPU and compare speeds
Friday 11 September 2026
Assembled automatically. No notes, because those are written by a person.
New work across every platform, newest first.
Benchmark any LM <1B params on CPU and compare speeds
After reproduction for gradio-app/gradio#9853 using the preview package built from PR #13851.
Before reproduction for gradio-app/gradio#9853 using the latest released Gradio package.
NVIDIA cash flows, scenarios, and break-even valuation.
Krea 2 Turbo text2image and image editing
This is a Gradio app for Hugging Face Spaces. It reads Supabase state on the
Exploratory behavioral reasoning with Llama 3.1
Multilingual speech recognition with frozen Gabor kernels
Generate videos from first & last frame + text using Wan2.1
Baseline reproduction for Gradio issue #5049 using the latest stable Gradio release. Event registration displays the unsupported inputs_kwargs error; compare it with the fixed Space.
Fixed reproduction for Gradio PR #13850 using its preview wheel. The Greet event passes Last name through inputs_kwargs; compare it with the baseline Space.
Full React + FastAPI research application with embeddings, FAISS retrieval, severity classification and live LLM explanations.
Krea 2 Turbo text2image and image editing
An MCP server that wraps the public
Multimodal completions with the Gemma 4 MoE base model
Your organization’s own USD asset library and downloads.
MiniMax-H3 Turbo LoRAs 4-step & 8-step Video Demo
This project demonstrates how to build an agentic system using Large Language Models (LLMs) that can interact with multiple databases and utilize various tools. It highlights the use of SQL agents to efficiently query large databases. The key frameworks used in this project include Google Gemini,…
Remove/Change background of video.
This is my Week 3 assignment for AI-Driven Finance. It's a 10-year DCF model
Singularities and the Navier–Stokes equ… — a Tangible lesson
Apply the motion of a video on a portrait
Reachy Mini controls Sonos by saying Hey Sonos.
Running on Hugging Face Spaces.
Generate songs and covers from style prompts and lyrics.
Bimanual 3D hand motion from egocentric video
This is a medical chat interface built with gradio.
Real Gradio on a server; the author stays credited
Edit /src/streamlit_app.py to customize this app to your heart's desire. :heart:
Kandinsky 5 backend for a vertical photo kiosk
Pick a held-out test-set transaction to compare a feature-only XGBoost
Unified speech generation and editing with AuK
ระบบ AI ตรวจจับและให้ความรู้เกี่ยวกับข้อความหลอกลวง (Scam)
Image-only MiniMax H3: text to image, image editing, up to nine reference images, and native H3 Fun ControlNet. No video endpoint or Colab dependency.
AudioCraft is a PyTorch library for deep learning research on audio generation. AudioCraft contains inference and training code
Open-source face-level AI image analysis research prototype