Running on Zero
MCP
Featured
77
JEV-9B — typed decisions
⚖
Calibrated typed decisions + System 2 reasoning
Spaces of the week
5 Oct 2026
Running on Zero
MCP
Featured
77
Kev
⚡
Typed questions in, calibrated probabilities out
Running
Featured
16
S1MB Leaderboard
📊
Compare System One models across 100+ specialized benchmarks
Running
Featured
25
Agate WebGPU
🚀
Agate text-to-image, 100% in your browser on WebGPU
Running on Zero
Agents
Featured
58
MiniMax-H3 Character Swap LoRA
🎭
Swap one character in a clip for a reference character
Running on Zero
MCP
Featured
13
LTX-2.5 22B Alpha Gen · Video to Alpha Matte
🎞
Turn an RGB video into a frame-aligned alpha matte
Running
Featured
102
Model Pulse
📈
Hugging Face model download stats, history & trends
Running on Zero
Agents
Featured
5
PixelUMM
🎨
Encoder-free unified image/video understanding + generation
All running apps, trending first
13 13 Spaces
Running
5
Paper Pulse
📄
Upvote history of every Hugging Face Daily Paper
Running
Featured
129
Open-LLM performances are plateauing, let’s make the leaderboard steep again
🏔
Explore and compare advanced language models on a new leaderboard
Runtime error
5
BenchBench Leaderboad
🏋
Runtime error
8
BenchBench Leaderboad
🏋
Compare benchmarks for language models
Build error
1
Safety BAT
🏋
Sleeping
DeployPythonicRAG
📉
Chat with your documents
Sleeping
DeployPythonicRAG
📉
Chat with an AI assistant
Build error
BenchBench Leaderboad
🏋
Compare benchmarks for language models
Sleeping
Agents
2
LLM Propensity Evals
🏆
Measuring propensities / alignment of the top HF models
Sleeping
LeniencyBench
📉
Measure and reduce leniency bias in LLMs via API
Running
CogBench Leaderboard
📊
Bloom-aligned LLM question-generation benchmark
Running
4
Benchmark Holo Deck
🌈
Explore LLM benchmarks with visual rarity cards
Running
Local Pro — IFEval Results
📊
MacBook Pro local LLM evaluation results; no live inference.