Models
Datasets
Spaces
Buckets new
Docs
Enterprise
Pricing
- Website
- Community
- Solutions
Log In
Sign Up

Collections

Discover the best community collections!

Collections trending this week

Datasets used to train our custom models used in our Browser AI Assistant

bravesoftware/diverse-llm-prompts-34k

Viewer • Updated 22 days ago • 34.8k • 15 • 1
bravesoftware/long-context-multimodal-conversations-5k

Viewer • Updated 2 days ago • 5.03k • 51 • 1
bravesoftware/lynx-search-query-generation

Viewer • Updated 2 days ago • 9.09k • 21 • 1

'Aether' Foundation Model

FINAL-Bench/Aether-7B-5Attn

Text Generation • 7B • Updated Jul 23 • 318 • 55
FINAL-Bench/Aether-7B-5Attn-it

Text Generation • 7B • Updated Jul 23 • 208 • 42
Paused

37

Aether-7B-5Attn — 100% Open-source Foundation Model: Sovereign AI

🌏

37

100% open-source sovereign foundation model (Apache-2.0)
FINAL-Bench/Aether-7B-5Attn-checkpoints

Updated Jul 20 • 64 • 30

Qwen3.6 Pi-Tune

Releases of Qwen3.6 family models fine tuned with the goal of improving agentic coding quality with PI

bytkim/Qwen3.6-27B-MTP-pi-tune-GGUF

Text Generation • 27B • Updated Jun 15 • 193k • 127
bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF

Image-Text-to-Text • 27B • Updated Jun 20 • 913 • 59

Nemotron-Labs-Audex

Unified Audio Intelligence Without Regressing on Text Intelligence

Running on Zero

MCP

Featured

47

Nemotron-Labs-Audex

🎧

47

Unified audio-text intelligence
nvidia/Nemotron-Labs-Audex-30B-A3B

Text Generation • Updated Aug 13 • 405 • 179
nvidia/Nemotron-Labs-Audex-2B

Text Generation • Updated Aug 18 • 1.09k • 92
Unified Audio Intelligence Without Regressing on Text Intelligence

Paper • 2607.05196 • Published Jul 6 • 23

VKAE Accelerated

Fastest single-GPU serving of open models via VKAE. Live board: hf.co/spaces/VIDraft/vkae. Each = card + Docker.

FINAL-Bench/Qwen3.5-35B-A3B-VKAE

Text Generation • Updated Jul 23 • 45
FINAL-Bench/Darwin-36B-Opus-VKAE

Text Generation • Updated Jul 4 • 40

Extremely compressed LLMs for deployment on edge devices

TheStageAI/gemma-4-12B-it-GGUF

Text Generation • 12B • Updated Jul 21 • 762 • 6
TheStageAI/gemma-4-E4B-it-GGUF

Text Generation • 7B • Updated Jul 21 • 768 • 3
TheStageAI/gemma-4-E2B-it-GGUF

Text Generation • 5B • Updated Jul 21 • 1.14k • 1
TheStageAI/Qwen3.5-9B-GGUF

Text Generation • 9B • Updated Jul 21 • 902 • 3

Collection of Wan 2.2 related models and LoRAs.

rzgar/Wan2.2_I2V_R1_base_v2

Image-Text-to-Video • Updated Jul 27 • 61 • 1
rzgar/Wan2.2_I2V_LightX2V_Slow-Mo_Fix

Image-to-Video • Updated Jul 29 • 924 • • 4
rzgar/Wan2.2-I2V-Weak-ID

Text-to-Image • Updated Jul 19 • 161 • • 2
rzgar/NSFW-Wan-UMT5-XXL-V2

Updated Jul 17 • 146 • 19

Alibaba-DAMO-Academy/RynnWorld-4D

Image-to-Video • Updated Jul 6 • 10
Alibaba-DAMO-Academy/RynnWorld-Teleop-Causal

Image-to-Video • Updated Jul 5 • 38 • 1
Alibaba-DAMO-Academy/RynnWorld-Teleop

Image-to-Video • Updated Jul 5 • 47 • 7
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published Jul 7 • 41

Running

Featured

467

Bonsai 27B WebGPU Kernels

🌳

467

Run a 1-bit 27B LLM locally in your browser on WebGPU
Paused

Agents

44

Ternary Bonsai 27B API Demo

🤗

44

Chat with the Bonsai 27B AI model in real time
prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 27B • Updated Aug 31 • 610k • • 1.41k
prism-ml/Bonsai-27B-gguf

Text Generation • 27B • Updated Jul 17 • 415k • 892

MDF - Research Commons Datasets

University of Waikato Research Commons publications (to June 2026) used for academic text analysis and classification research.

dinushiTJ/nz_research_commons_classification

Viewer • Updated Jun 25 • 16.6k • 35 • 2
dinushiTJ/nz_research_commons_embedding_triplets_10k

Viewer • Updated Jun 1 • 13.3k • 32
dinushiTJ/nz_research_commons_embedding_triplets_5k

Viewer • Updated Jun 2 • 8.32k • 17
dinushiTJ/nz-research-commons-llama-groq-label-mismatches

Viewer • Updated Jun 28 • 107 • 5

Datasets used to train our custom models used in our Browser AI Assistant

bravesoftware/diverse-llm-prompts-34k

Viewer • Updated 22 days ago • 34.8k • 15 • 1
bravesoftware/long-context-multimodal-conversations-5k

Viewer • Updated 2 days ago • 5.03k • 51 • 1
bravesoftware/lynx-search-query-generation

Viewer • Updated 2 days ago • 9.09k • 21 • 1

Extremely compressed LLMs for deployment on edge devices

TheStageAI/gemma-4-12B-it-GGUF

Text Generation • 12B • Updated Jul 21 • 762 • 6
TheStageAI/gemma-4-E4B-it-GGUF

Text Generation • 7B • Updated Jul 21 • 768 • 3
TheStageAI/gemma-4-E2B-it-GGUF

Text Generation • 5B • Updated Jul 21 • 1.14k • 1
TheStageAI/Qwen3.5-9B-GGUF

Text Generation • 9B • Updated Jul 21 • 902 • 3

'Aether' Foundation Model

FINAL-Bench/Aether-7B-5Attn

Text Generation • 7B • Updated Jul 23 • 318 • 55
FINAL-Bench/Aether-7B-5Attn-it

Text Generation • 7B • Updated Jul 23 • 208 • 42
Paused

37

Aether-7B-5Attn — 100% Open-source Foundation Model: Sovereign AI

🌏

37

100% open-source sovereign foundation model (Apache-2.0)
FINAL-Bench/Aether-7B-5Attn-checkpoints

Updated Jul 20 • 64 • 30

Collection of Wan 2.2 related models and LoRAs.

rzgar/Wan2.2_I2V_R1_base_v2

Image-Text-to-Video • Updated Jul 27 • 61 • 1
rzgar/Wan2.2_I2V_LightX2V_Slow-Mo_Fix

Image-to-Video • Updated Jul 29 • 924 • • 4
rzgar/Wan2.2-I2V-Weak-ID

Text-to-Image • Updated Jul 19 • 161 • • 2
rzgar/NSFW-Wan-UMT5-XXL-V2

Updated Jul 17 • 146 • 19

Qwen3.6 Pi-Tune

Releases of Qwen3.6 family models fine tuned with the goal of improving agentic coding quality with PI

bytkim/Qwen3.6-27B-MTP-pi-tune-GGUF

Text Generation • 27B • Updated Jun 15 • 193k • 127
bytkim/Qwen3.6-27B-MTP-pi-reasoning-GGUF

Image-Text-to-Text • 27B • Updated Jun 20 • 913 • 59

Alibaba-DAMO-Academy/RynnWorld-4D

Image-to-Video • Updated Jul 6 • 10
Alibaba-DAMO-Academy/RynnWorld-Teleop-Causal

Image-to-Video • Updated Jul 5 • 38 • 1
Alibaba-DAMO-Academy/RynnWorld-Teleop

Image-to-Video • Updated Jul 5 • 47 • 7
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published Jul 7 • 41

Nemotron-Labs-Audex

Unified Audio Intelligence Without Regressing on Text Intelligence

Running on Zero

MCP

Featured

47

Nemotron-Labs-Audex

🎧

47

Unified audio-text intelligence
nvidia/Nemotron-Labs-Audex-30B-A3B

Text Generation • Updated Aug 13 • 405 • 179
nvidia/Nemotron-Labs-Audex-2B

Text Generation • Updated Aug 18 • 1.09k • 92
Unified Audio Intelligence Without Regressing on Text Intelligence

Paper • 2607.05196 • Published Jul 6 • 23

Running

Featured

467

Bonsai 27B WebGPU Kernels

🌳

467

Run a 1-bit 27B LLM locally in your browser on WebGPU
Paused

Agents

44

Ternary Bonsai 27B API Demo

🤗

44

Chat with the Bonsai 27B AI model in real time
prism-ml/Ternary-Bonsai-27B-gguf

Text Generation • 27B • Updated Aug 31 • 610k • • 1.41k
prism-ml/Bonsai-27B-gguf

Text Generation • 27B • Updated Jul 17 • 415k • 892

VKAE Accelerated

Fastest single-GPU serving of open models via VKAE. Live board: hf.co/spaces/VIDraft/vkae. Each = card + Docker.

FINAL-Bench/Qwen3.5-35B-A3B-VKAE

Text Generation • Updated Jul 23 • 45
FINAL-Bench/Darwin-36B-Opus-VKAE

Text Generation • Updated Jul 4 • 40

MDF - Research Commons Datasets

University of Waikato Research Commons publications (to June 2026) used for academic text analysis and classification research.

dinushiTJ/nz_research_commons_classification

Viewer • Updated Jun 25 • 16.6k • 35 • 2
dinushiTJ/nz_research_commons_embedding_triplets_10k

Viewer • Updated Jun 1 • 13.3k • 32
dinushiTJ/nz_research_commons_embedding_triplets_5k

Viewer • Updated Jun 2 • 8.32k • 17
dinushiTJ/nz-research-commons-llama-groq-label-mismatches

Viewer • Updated Jun 28 • 107 • 5

Previous
1
...
33
34
35
36
37
...
23,808
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs