Home / Models
Model weights you can download. updated 73 minutes ago.
527 projects tracked. Median star gain over 7 days: +18. Categories come from GitHub topics, Hugging Face tags and the project description.
Official implementation of LittleBit (NeurIPS 2025) and its follow-up LittleBit-2 (ICML 20...
TOO EARLY 75 4 +28 to +67 +385 20.0x Accelerating52% of its stars arrived in the last 7 days. Gaining 20.0x its usual weekly pace. No Hacker News posts in the last 7 days.
Humanoid whole-body motion tracking with one differentiable world model.
TOO EARLY 74 43 +3 to +45 +405 13.4x Quiet climber21% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
Rust, created Oct 2026
TOO EARLY 94 48 +22 to +64 +118 11.8x Watching24% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
The first open-source model for code-driven video creation.
TOO EARLY 65 14 +12 to +52 +101 7.7x Watching13% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transfor...
REAL 62 77 -15 +75 7.5x Watching15% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
MiniMax-H3-Image, an open-weight model for 16-megapixel image generation and editing.
TOO EARLY 63 27 +0 to +42 +75 7.5x Watching17% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
Turkish voice design with VoxCPM2 on a 4 GB GPU: describe a voice, pick a variant, read te...
REAL 62 69 -7 +73 7.3x Watching15% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
Naive-N0.5-Flash is an open-weight 309B MoE model with 15.5B active parameters, built for...
TOO EARLY 62 0 +23 to +57 +72 7.1x Watching12% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protect...
REAL 95 92 +4 +673 5.9x Quiet climber11% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative...
TOO EARLY 70 32 +4 to +46 +195 4.2x Watching8% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
Fast, accurate OCR with correctness assessment.
REAL 62 73 -11 +73 3.9x Watching7% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
WeVisOne-VL is a powerful VLM by the WeChat Vision Team at Tencent, unifying object-level...
TOO EARLY 61 12 +10 to +50 +62 2.6x Watching5% of its stars arrived in the last 7 days. No Hacker News posts in the last 7 days.
Training-free language model modification: Remove censorship, suppress slop, reduce sycoph...
TOO EARLY 98 67 +24 to +46 +1,901 1.5x Surging4% of its stars arrived in the last 7 days. Gaining 1.5x its usual weekly pace. No Hacker News posts in the last 7 days.
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek...
REAL 81 98 -17 +411 1.3x Quiet climber1% of its stars arrived in the last 7 days. Gaining 1.3x its usual weekly pace. No Hacker News posts in the last 7 days.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning model...
REAL 82 98 -17 +348 1.2x Quiet climber0% of its stars arrived in the last 7 days. Gaining 1.2x its usual weekly pace. No Hacker News posts in the last 7 days.
ODS V3 Pre-Release: Public testing and refinement ahead of the official V3 launch. Turn yo...
REAL 62 78 -16 +65 1.0x Watching1% of its stars arrived in the last 7 days. Gaining 1.0x its usual weekly pace. No Hacker News posts in the last 7 days.
Uncensored Open-source alternative to AI video platforms — Free AI image & video generatio...
REAL 88 69 +19 +936 0.9x Quiet climber3% of its stars arrived in the last 7 days. Gaining 0.9x its usual weekly pace. No Hacker News posts in the last 7 days.
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and...
TOO EARLY 72 15 +18 to +58 +128 0.8x Watching10% of its stars arrived in the last 7 days. Gaining 0.8x its usual weekly pace. No Hacker News posts in the last 7 days.
World's first open-source, agentic video production system. 12 production pipelines, 100+...
REAL 90 85 +5 +1,645 0.6x Surging2% of its stars arrived in the last 7 days. Gaining 0.6x its usual weekly pace. No Hacker News posts in the last 7 days.
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice...
REAL 99 99 +0 +5,223 0.6x Surging4% of its stars arrived in the last 7 days. Gaining 0.6x its usual weekly pace. No Hacker News posts in the last 7 days.
Distill a good Claude Code / Codex session into a skill an open-weight model can follow to...
first seen 16h ago, repo created 21 Nov 2026
MID 42 29 +13 - WatchingKobiMusic's multi-instrument audio-to-MIDI transcriber: notes, instrument tracks and drums...
first seen 24h ago, repo created 16 Nov 2026
MID 42 57 -15 +55 WatchingCalibrated internal-state modulation, readout, and neural observability for local dense la...
first seen 47h ago, repo created 14 Nov 2026
MID 42 24 +18 +47 WatchingTraining Reasoning Models in Simulation to Natively Use Real Robots
first seen 6d ago, repo created 13 Nov 2026
MID 42 53 -11 +12 WatchingPro Tools 2026 desktop setup with multitrack editing, MIDI sequencing, VST hosting and a p...
first seen 6d ago, repo created 14 Nov 2026
MID 42 47 -5 0 WatchingA 4.5M-parameter two-voice English text-to-speech model, trained from scratch
first seen 6d ago, repo created 14 Nov 2026
SLEEPER 42 83 -41 +33 WatchingMiniMax-H3-Image, an open-weight model for 16-megapixel image generation and editing.
first seen 9d ago, repo created 9 Nov 2026
TOO EARLY 63 27 +0 to +42 +6 WatchingTraining code for PAN2, a open foundation world model for physical intelligence
first seen 10d ago, repo created 5 Nov 2026
TOO EARLY 57 9 +7 to +47 +1 WatchingDownload and explore time-series datasets through one standardized format.
first seen 10d ago, repo created 8 Jul 2026
REAL 91 80 +11 +1 WatchingCompress any LLM in seconds, load it for inference and in one click you have an AI that co...
first seen 10d ago, repo created 8 Nov 2026
TOO EARLY 83 26 +20 to +62 0 WatchingPublic code release for the paper "The Surprising Effectiveness of Deleting Weights in LLM...
first seen 10d ago, repo created 10 Nov 2026
TOO EARLY 56 18 -1 to +41 +2 WatchingTernary language models on a home computer: run, train, convert, fine-tune, export to GGUF
first seen 10d ago, repo created 9 Nov 2026
OVERHYPED 90 39 +51 0 WatchingQwen3.5 / 3.8 to ternary with TTF-trainable ternary adapters
first seen 10d ago, repo created 24 Oct 2026
TOO EARLY 82 34 +14 to +56 0 WatchingTwo-timescale threshold flips (TTF): training and converting ternary {-1,0,1} LLMs without...
first seen 10d ago, repo created 31 Aug 2026
MID 85 59 +25 +3 WatchingHumanoid whole-body motion tracking with one differentiable world model.
first seen 11d ago, repo created 10 Nov 2026
TOO EARLY 74 43 +3 to +45 +14 Quiet climberNaive-N0.5-Flash is an open-weight 309B MoE model with 15.5B active parameters, built for...
first seen 11d ago, repo created 27 Sep 2026
TOO EARLY 62 0 +23 to +57 +13 Watching🔥🔥 The extremely fast inference engine for decision model
first seen 12d ago, repo created 24 Oct 2026
REAL 93 78 +15 0 WatchingOpenAmika: MekaHime's AI companion Amika, open source. Live2D avatar, real-time voice, lon...
first seen 16d ago, repo created 3 Nov 2026
REAL 59 74 -15 0 Watching:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transfor...
first seen 17d ago, repo created 31 Oct 2026
REAL 62 77 -15 +2 WatchingA frontier model edits another model's weights by hand (Gemma 4 12B, EN->IT tense). Plus a...
first seen 17d ago, repo created 3 Nov 2026
MID 22 25 -3 0 WatchingNo Hacker News points in the last 7 days.