zai-org/GLM-5.2
text-generation · transformers, safetensors, glm_moe_dsa
Home / 🧠 LLM Models / Weights
🧠 LLM Models / Weights
86 View all · Daily curated AI / LLM open-source intelligence, with plain-language notes and license checks.
nvidia/Qwen3.6-35B-A3B-NVFP4
text-generation · Model Optimizer, safetensors, qwen3_5_moe
sapientinc/HRM-Text-1B
text-generation · transformers, safetensors, hrm_text
tencent/Hy-MT2-1.8B
translation · transformers, safetensors, hunyuan_v1_dense
nvidia/GLM-5.2-NVFP4
text-generation · Model Optimizer, safetensors, glm_moe_dsa
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16
text-generation · transformers, safetensors, nemotron_h
google/tabfm-1.0.0-pytorch
tabular-classification · tabfm, safetensors, tabular
nvidia/NVIDIA-Nemotron-Labs-3-Puzzle-75B-A9B-NVFP4
text-generation · transformers, safetensors, nemotron_h_puzzle
nvidia/diffusiongemma-26B-A4B-it-NVFP4
text-generation · safetensors, diffusion_gemma, nvidia
deepseek-ai/DeepSeek-V4-Pro-DSpark
text-generation · transformers, safetensors, deepseek_v4
meituan-longcat/LongCat-2.0
text-generation · LongCat-2.0, safetensors, transformers
WeiboAI/VibeThinker-3B
text-generation · transformers, safetensors, qwen2
tencent/Hy-MT2-30B-A3B
translation · transformers, safetensors, hy_v3
robbyant/lingbot-video-moe-30b-a3b
· diffusers, safetensors, license:apache-2.0
JetBrains/Mellum2-12B-A2.5B-Thinking
text-generation · transformers, safetensors, mellum
AliesTaha/fable-traces
text-generation · transformers, safetensors, qwen3
SupraLabs/Supra-Router-51M
text-generation · transformers, safetensors, llama
openbmb/MiniCPM-RobotManip
robotics · transformers, safetensors, minicpm_vla
LiquidAI/LFM2.5-8B-A1B
text-generation · transformers, safetensors, lfm2_moe
tencent/Hy3
text-generation · transformers, safetensors, hy_v3
nationaldesignstudio/rampart
token-classification · transformers.js, onnx, bert
silx-ai/Quasar-Preview
text-generation · transformers, safetensors, quasar_long
jlnsrk/GLM-5.2-colibri-int4
· glm_moe_dsa, int4, cpu
OpenMOSS-Team/MOSS-VL-Realtime
video-text-to-text · transformers, safetensors, moss_vl
openai/privacy-filter
token-classification · transformers, onnx, safetensors
openbmb/UltraX-Preview
· task_categories:text-generation, language:en, license:apache-2.0
openbmb/MiniCPM5-1B
text-generation · transformers, safetensors, llama
nvidia/Nemotron-Labs-Diffusion-14B
text-generation · transformers, safetensors, nvidia
OpenMOSS-Team/MOSS-Transcribe-Diarize
audio-text-to-text · transformers, safetensors, moss_transcribe_diarize
Soofi-Project/Soofi-S-Base
text-generation · transformers, safetensors, soofi
lazarus19/Vibe-Coding-Instruct
· task_categories:text-generation, language:en, license:apache-2.0
OpenOneRec/Explorer_LLM_Rec_Competition
· region:us
LiquidAI/LFM2.5-Embedding-350M
sentence-similarity · sentence-transformers, safetensors, lfm2
Qwen/Qwen-Image-Bench
· task_categories:image-to-text, language:en, language:zh
ServiceNow-AI/eva-bench
· task_categories:text-generation, task_categories:other, language:en
nvidia/Nemotron-Personas-Vietnam
· task_categories:text-generation, language:vi, license:cc-by-4.0
FINAL-Bench/Aether-Sovereign-AI
· docker, sovereign-ai, open-source-llm
scholarweave/arxiv-latex
· task_categories:text-generation, task_categories:feature-extraction, language:en
ReasonCore/open-spatial-reasoning
· task_categories:multiple-choice, language:en, license:cc-by-4.0
greghavens/kimi-k3-coding-and-debugging-traces
· task_categories:text-generation, annotations_creators:machine-generated, language:en
amphora/ResearchMath-14k
· task_categories:text-generation, task_categories:question-answering, language:en
nvidia/Nemotron-Personas-El-Salvador
· task_categories:text-generation, language:es, license:cc-by-4.0
FINAL-Bench/Aether-7B-5Attn-checkpoints
· language:en, language:ko, license:apache-2.0
armand0e/qwen3.7-max-pi-traces
· task_categories:text-generation, size_categories:n<1K, format:json
rl-llm-wiki/rl-wiki
· static, region:us
actava/chi-bench
· task_categories:text-generation, language:en, license:apache-2.0
nvidia/Nemotron-Personas-Belgium
· task_categories:text-generation, language:nl, language:fr
GD-ML/TransitLM
· task_categories:text-generation, language:zh, license:cc-by-nc-4.0
CausalLM/Kingfall-Roleplay
· language:en, language:zh, language:ja
ByteDance-Seed/EdgeBench
· task_categories:text-generation, language:en, license:cc-by-4.0
ginigen-ai/Metacognition-Bench
· task_categories:text-generation, task_categories:question-answering, language:en
nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16
text-generation · transformers, safetensors, nvidia
QuixiAI/QuixiMath-1B
· task_categories:text-generation, task_ids:language-modeling, language:en
zhiqix/PUM-MATH
· task_categories:text-generation, task_categories:text-classification, language:en
YuCrazing1/ClothTransformer-dataset
· language:en, license:cc-by-4.0, size_categories:1K<n<10K
yatin-superintelligence/digital-hospital-environment
· task_categories:text-generation, task_categories:question-answering, task_categories:reinforcement-learning
froggeric/Qwen-Fixed-Chat-Templates
· mlx, jinja, chat-template
SupraLabs/supra-reasoning-corpus-4K-5M-v1
· task_categories:text-generation, language:en, license:apache-2.0
SupraLabs/reasoning-summaries-61k
· task_categories:summarization, task_categories:text-generation, language:en
ajibawa-2023/Shell-Code-Large
· task_categories:text-generation, language:en, license:mit
makora-ai/triton-gpu-latency
· task_categories:text-generation, language:en, license:apache-2.0
AlienKevin/SWE-ZERO-12M-trajectories
· task_categories:text-generation, language:en, license:apache-2.0
codeparrot/github-code
· task_categories:text-generation, task_ids:language-modeling, language_creators:crowdsourced
trillionlabs/TheBioCollection
· task_categories:text-generation, language:en, size_categories:10M<n<100M
LiquidAI/antidoom-mix-v1.0
· task_categories:text-generation, language:en, license:apache-2.0
Extraltodeus/J-Wash
Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.
ministere-culture/comparia-fr-arena
· task_categories:text-generation, language:fr, license:etalab-2.0
HuggingFaceFW/fineweb
· task_categories:text-generation, language:en, license:odc-by
MEDHARVIX-SYSTEMS/bhasaflow-khasi-monolingual-corpus-v1
· task_categories:text-generation, language:kha, license:cc-by-nc-4.0
MLNLP-World/Paper-Rebuttal-Tips
MLNLP社区用来帮助大家论文Rebuttal的整理仓库。
roneneldan/TinyStories
· task_categories:text-generation, language:en, license:cdla-sharing-1.0
Qwen/Qwen3-TTS
· gradio, region:us
allenai/c4
· task_categories:text-generation, task_categories:fill-mask, task_ids:language-modeling
IlyaGusev/habr
· task_categories:text-generation, language:ru, language:en
badlogicgames/pi-mono
· task_categories:text-generation, language:en, language:code
mikeee/qwen-7b-chat
· docker, region:us
AlicanKiraz0/Turkce-Atlas-Instruct
· task_categories:text-generation, task_categories:question-answering, task_categories:summarization
openbmb/Ultra-FineWeb-L3
· task_categories:text-generation, language:en, language:zh
hao-ai-lab/JetSpec
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Causal Parallel Tree Drafting
Qwen/WebWorldData
· task_categories:text-generation, language:en, language:zh
PolyX-Research/Robust-U1
🚀🚀🚀 [ICML 2026] Official Implementation of Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
minhxthanh/Vietnam-History-1M-Vi
· task_categories:question-answering, task_categories:text-generation, language:vi
oliviazzzu/minimal-embodiment
A minimal hardware-software architecture giving large language models a closed-loop physical embodiment with self-perception loops.
alibayram/identity_finetune_magibu_q3
· task_categories:text-generation, language:tr, language:en
czg1225/DMax
DMax: Aggressive Parallel Decoding for dLLMs
livehl/aimirror
🚀 200倍速！AI时代的下载神器 | Docker/PyPI/HuggingFace/CRAN 全加速 | 并行分片+智能缓存，让下载飞起来