Intern S2 preview 🔥 A scientific multimodal model from Shanghai AI Lab huggingface.co/internlm/Int...

Ant group just dropped Ring-2.6-1T 🔥 1T reasoning model, built for real world agent workflows. ✨ MIT license ✨ 128K >> 256K context (YaRN) ✨ Async RL + IcePop training architecture ✨ Dual reasoning : "high" for fast agent loops, "xhigh" for deep reasoning = Better cost/performance tradeoff 👀

Ant group just dropped Ring-2.6-1T 🔥 1T reasoning model, built for real world agent workflows. ✨ MIT license ✨ 128K >> 256K context (YaRN) ✨ Async RL + IcePop training architecture ✨ Dual reasoning: "high" for fast agent loops, "xhigh" for deep reasoning = Better cost/performance tradeoff 👀

Ant group just dropped Ring-2.6-1T 🔥 1T reasoning model, built for real world agent workflows. ✨ MIT license ✨ 128K >> 256K context (YaRN) ✨ Async RL + IcePop training architecture ✨ Dual reasoning: "high" for fast agent loops, "xhigh" for deep reasoning = Better cost/performance tradeoff

MemPrivacy ㊙️ a lightweight privacy preserving model for edge cloud AI agents from MemTensor. huggingface.co/collections/... ✨ 1.7B/4B - RL/SFT ✨ High precision privacy extraction ✨ 4 level privacy taxonomy (PL1–PL4) ✨ Semantic preserving typed placeholders

MiniCPM V4.6 🔥 a 1B MLLM that actually runs on your phone, just released by OpenBMB huggingface.co/openbmb/Mini... ✨ 1B - Apache2.0 ✨ Runs on iOS, Android, HarmonyOS ✨ ~1.5× faster throughput than Qwen3.5 0.8B ✨ Mixed 4x/16x visual token compression

Qwen released WebWorld 🌍 an open world model series for web agents ✨ 8B/14B/32B+Dataset ✨Apache2.0 ✨+9.9% MiniWob++, +10.9% WebArena ✨ Matches Claude Opus 4.1 & Gemini 3 Pro on factuality，beats GPT-5 as world model ✨Unified action space, 30+ step simulation, 5 state formats

Ling-2.6-1T just dropped by Antgroup , one day after Ling 2.6 Flash. Both optimized for the same goal: usable intelligence at the lowest token cost 💰 ✨ MLA + Linear Attention hybrid for long context efficiency ✨ Answers without verbose CoT, lower token cost ✨ 1T / 63B active ✨ MIT license

SenseTime is back to open source with SenseNova U1 🔥 A unified multimodal model in collab with MMLab NTU huggingface.co/collections/... ✨ no visual encoder & VAE ✨ NEO Unify end to end ✨ End-to-end pixel–word modeling

MiMo-V2.5 🔥 a native omni modal MoE built for agents released by XiaomiMiMo huggingface.co/collections/... ✨Base (310B total / 15B active) & Pro (1T total / 42B active) ✨MIT license ✨Text + image + video + audio ALL IN ONE ✨Up to 1M context ✨Agentic RL + MOPD post-training

DeepSeek V4 🐳🔥 makes 1M token context & SOTA Agentic/coding more accessible!! huggingface.co/collections/... ✨Pro (1.6T/49B active) & Flash (284B/13B active) ✨1M token context ✨LiveCodeBench 93.5 🤯 beats Gemini 3.1 Pro & Opus 4.6 ✨MIT licensed

LLaDA2.0-Uni from Antgroup is an interesting direction 👀 huggingface.co/inclusionAI/... ✨ 16B MoE/ 1B active per token ✨ Unifies generation + understanding + reasoning in a single diffusion LLM ✨ MoE backbone + diffusion decoder ✨ Apache 2.0

MiMo-V2.5-ASR 🔥 new ASR model from Xiaomi Model: huggingface.co/XiaomiMiMo/M... Demo: huggingface.co/spaces/Xiaom... ✨ MIT license ✨ Support Mandarin, English & Chinese dialects ✨ Code-switching (no language tags needed) ✨ Multi-speaker / meetings ✨ Noisy & far-field audio

Tencent just released HY3 preview on @hf.co First drop from TencentHunyuan rebuilt infra👀 Model: huggingface.co/collections/... Demo: huggingface.co/spaces/tence... ✨ 295B MoE /21B active ✨ 256k context ✨ Hybrid fast/slow thinking ✨ Solid BrowseComp & WideSearch (search agents)

Qwen3.6-27B just dropped on @huggingface 🔥 huggingface.co/Qwen/Qwen3.6... huggingface.co/Qwen/Qwen3.6... ✨ 27B dense model ✨ 262K native context, scalable to 1M+ tokens ✨ Vision + language in one model ✨ 77.2 on SWE-bench Verified

Kimi 2.6 is now available on @hf.co 🔥🎉 huggingface.co/moonshotai/K... ✨ 1T MoE / 32B active / 256K context ✨ Agent Swarm: 300 sub-agents × 4,000 steps ✨ Modified MIT

MOSS-VL 🔥 Vision model from Open MOSS Model: huggingface.co/collections/... Demo: huggingface.co/spaces/OpenM... ✨ 11B - Apache 2.0 ✨ Cross-attention + XRoPE (3D: time, height, width) ✨ Beats Qwen3-VL-8B by 8.3 pts on VSI-bench

Baidu just released ERNIE-Image on Hugging Face🔥 Model: huggingface.co/collections/... Demo: huggingface.co/spaces/baidu... ✨ 8B DiT - Image/Image Turbo ✨ Apache2.0 ✨ Strong text rendering for posters & UI-style images ✨ Structured outputs (comics, multi-panel scenes)

A new large-scale RGB-D dataset from Ant Group: LingBot-Depth 🤖 huggingface.co/datasets/rob... ✨3M+ samples / 2.7TB ✨Real-world + simulation + VLA robotics data ✨Raw sensor depth + ground truth

LongCat-AudioDiT 🔊New TTS from Meituan LongCat team huggingface.co/meituan-long... ✨ 1B & 3.5B - MIT license ✨ Diffusion + non-AR generation ✨ Operates directly in waveform latent space ✨ Simpler pipeline (no mel-spectrograms)

Matrix-Game 3.0🔥real-time interactive world models from Skywork huggingface.co/Skywork/Matr... ✨ MIT license ✨ 720p @ 40FPS with a 5B model ✨ Minute-long memory consistency ✨ Unreal + AAA + real-world data ✨ Scales up to 28B MoE

daVinci-LLM 🔥 The SII-GAIR team just shared the full training pipeline on @hf.co huggingface.co/SII-GAIR-NLP... ✨ 3B, competitive with 7B models ✨ 8T-token transparent training ✨ 200+ ablation studies ✨ Data Darwinism (L0–L9) framework

LongCat-Next 🐱 A multimodal foundation model released by Meituan huggingface.co/meituan-long... ✨ 74B total - 3B active - MIT ✨ One token space for all modalities ✨ DiNA paradigm for unified learning ✨ Seeing, creating, talking all in one

PrismAudio 🔥 RL-powered video-to-audio (V2A) framework from Alibaba FunAudio team Model: huggingface.co/FunAudioLLM/... Paper: huggingface.co/papers/2511.... Demo: huggingface.co/spaces/FunAu...

LongCat-Flash-Prover 🐱 A 560B MoE from Meituan just dropped on @hf.co huggingface.co/meituan-long... ✨ MIT license ✨ Native Formal Reasoning: Auto-formalize, sketch & verify proofs live in Lean4 ✨ 97.1% pass rate on MiniF2F-Test & 70.8% ProverBench

daVinci-MagiHuman 🎬 Human Centric Audio-Video Generative Model by GAIR Model: huggingface.co/GAIR/daVinci... Paper: huggingface.co/GAIR/daVinci... ✨ 15B – Fully open source! ✨ 5-sec 1080p video in 38s on one H100 ✨ Supports 6 languages ✨ Unified model with text + video + audio

AutoMathText-V2 🔥 A 2.46T token STEM dataset from Shanghai QI ZHI Institute huggingface.co/datasets/Ope... ✨ Optimized for Math & STEM ✨ Triple deduplication: Exact → Fuzzy → Semantic

Another OCR model just dropped 🔥 (so many OCRs lately!) dots.mocr from RedNote Hi Lab looks really impressive on the benchmarks. huggingface.co/collections/... ✨ 3B ✨ Multilingual support ✨ Converts charts, diagrams, and UI layouts directly into SVG code

Qianfan-OCR 🔥 New end-to-end document intelligence model from Baidu is now available on @hf.co huggingface.co/baidu/Qianfa... huggingface.co/papers/2603.... ✨ 4B - Apache 2.0 ✨ OCR across 192 languages ✨ 1 page/sec on a single A100 ✨ Trained on 1,024 Kunlun P800 chips

Xperience 10M 🔥 One of the largest egocentric multimodal datasets from Ropedia_ai huggingface.co/datasets/rop... ✨ 10M interactions ✨ 10k hours egocentric recordings ✨ RGB + audio + depth + SLAM + hand & body mocap + IMU ✨ Structured 3D/4D annotations

MiroThinker 1.7 🔥 New open research agents huggingface.co/collections/... ✨ 1.7 & 1.7 mini (30B) ✨ 256K context longth ✨ 300 tool calls per task ✨ Qwen3-based + custom agent (MiroThinker-H1)

Fish Audio S2 Pro 🔊 huggingface.co/collections/... ✨ Fine-grained prosody & emotion control ✨ Supports 80+ languages ✨ Low-latency streaming & long context inference

Yuan3.0 Ultra 🔥 A 1T multimodal LLM from YuanLab huggingface.co/YuanLabAI ✨ 64K context ✨ Enterprise-ready: RAG, summarization, Text-to-SQL ✨ 103-layer MoE w/ LAEP (49% efficiency boost)

IQuest-Coder-V1 Update! 7B & 14B series now on @hf.co 🔥 huggingface.co/collections/... ✨ 7B/14B - Base, instruct, thinking ✨ Optimized for tool use & CLI agents ✨ 128k context length

Step 3.5 Flash 🔥New MoE model from StepFun huggingface.co/stepfun-ai/S... huggingface.co/stepfun-ai/S... ✨ Base & Base-Midtrain ✨ 196B total/11B active - Apache 2.0 ✨ 256K context ✨ High-speed reasoning & agentic tasks

Qwen 3.5 Small Model Series just dropped on @hf.co 🔥 huggingface.co/collections/... ✨ 0.8B/2B/4B/9B ✨ Apache2.0 ✨ 262K→1M token context

MiniMax M2.5 is now available on @hf.co huggingface.co/MiniMaxAI/Mi... ✨ 229B - Modified MIT license ✨37% faster than M2.1 ✨ ~$1/hour at 100 TPS

Ovis2.6-30B-A3B🚀 The latest multimodal LLM from the AIDC team at Alibaba huggingface.co/AIDC-AI/Ovis... ✨ 64K context + 2880×2880 resolution ✨ MoE 30B/3B active ✨ Apache 2.0 ✨ “Think with Image” : Active visual reasoning

Ring-1T-2.5 🔥 1T reasoning model based on hybrid linear attention from Ant Group huggingface.co/inclusionAI/... ✨ MIT license ✨ 128K -> 256K (YaRN) ✨ Hybrid MLA + Lightning Linear Attention (1:7) ✨ Agentic: Natively with Claude Code & OpenClaw

RynnBrain 🤖 a physics aware embodied brain for robots from Alibaba DAMO huggingface.co/collections/... ✨ 2B/8B/30B (3B active) ✨ Apache 2.0 ✨ Understands egocentric scenes with strong spatial awareness ✨ Tracks objects and motion over time

MiniCPM-SALA 🚀 Hybrid model combining Sparse + Linear Attention from OpenBMB huggingface.co/openbmb/Mini... ✨ 25% Sparse + 75% Linear Attention ✨ Up to 3.5× faster inference ✨ 1M+ tokens on RTX 5090 / A6000D ✨ Apache 2.0

While Seedance 2.0’s videos are all over the timeline, DeepSeek quietly pushed a new model update in its app. GLM-5, Ming-flash-omni from Ant Group , MiniCPM-SALA from OpenBMB, and the upcoming MiniMax M2.5 keep the heat on 🔥 Spring Festival is around the corner, no one’s sleeping!

Ming-flash-omni 2.0 🚀 New open omni-MLLM released by Ant Group huggingface.co/inclusionAI/... ✨ MIT license ✨ MoE - 100B/6B active ✨ Zero-shot voice cloning + controllable audio ✨ Fine-grained visual knowledge grounding

New dataset 🔥 UltraData-Math 🔢 math pre-training dataset released by OpenBMB huggingface.co/datasets/ope... ✨ Apache2.0 ✨ 290B+ tokens with tiered quality (L1 → L3) ✨ Math-aware parsing that keeps formulas intact ✨ Proven to improve math reasoning (GSM8K & MATH500)

HY-1.8B-2Bit 🔥 A 2-bit on-device LLM released by Tencent huggingface.co/AngelSlim/HY... huggingface.co/AngelSlim/HY... ✨ GGUF available ✨ Near INT4 performance at just 2-bit, with full reasoning preserved

A bit late due to the flu 😅 but still very worth sharing: China open source highlights for January 2026🔥 huggingface.co/collections/...

LLaDA 2.1 is out 🔥 MoE diffusion language models released by AntGroup huggingface.co/inclusionAI/... huggingface.co/inclusionAI/... ✨LLaDA2.1-mini: 16B - Apache2.0 ✨LLaDA2.1-flash: 100B - Apache2.0 ✨Both delivers editable generation, RL-trained diffusion reasoning and fast inference

AI for science is moving fast🚀 Intern-S1-Pro 🔬 a MoE multimodal scientific reasoning model from Shanghai AI Lab , now live on @hf.co huggingface.co/internlm/Int... ✨ 1T total / 22B active ✨ Apache 2.0 ✨ SoTA scientific reasoning performance

✨ China’s open source AI ecosystem has entered a new phase This final blog in the series examines how leading Chinese AI organizations are evolving ,and what this implies for the future of open source. huggingface.co/blog/hugging...

LongCat Image-Edit-Turbo is now live on @hf.co huggingface.co/meituan-long... It's the distilled version of LongCat-Image-Edit from Meituan Longcat team , achieving a 10x speedup🚀