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

MIUProject/VNCCS_PoseLibrary_Main

Updated May 23

Running on Zero

MCP

2.1k

Wan2.2 14B Fast Preview

🐌

2.1k

generate a video from an image with a text prompt
Running on Zero

MCP

Featured

3.36k

Wan2.2 14B Fast

🎥

3.36k

generate a video from an image with a text prompt
Running on CPU Upgrade

Agents

2.24k

Omni Image Editor

🖼

2.24k

Image edit, text to image, image upscale, remove watermark

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Paper • 2607.02515 • Published 27 days ago • 19

deepreinforce-ai/Ornith-1.0-9B-GGUF

Text Generation • 9B • Updated Jun 25 • 4.07M • 576
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

Image-Text-to-Text • 9B • Updated 24 days ago • 90k • 286
DJLougen/Qwable-5-27B-Coder

Text Generation • 28B • Updated Jun 23 • 359 • • 42
DJLougen/Qwable-5-27B-Coder-GGUF

Text Generation • 27B • Updated Jun 23 • 9.43k • 16

Bitcoin-Anchored Provenance

Prove a record existed before a given Bitcoin block, verifiable offline with no operator in the trust path. Existence and ordering only.

MarkovianProtocol/bitcoin-anchored-ai-provenance

Viewer • Updated 3 days ago • 151 • 98
Running

MCP

Markovian Provenance

⚛

AI-output provenance, verifiable against Bitcoin. No trust.
Runtime error

Agents

canoncheck

🔁

Cross-language canonical JSON + sha256/keccak256 (RFC 8785)

Attention Is All You Need

Paper • 1706.03762 • Published Jun 12, 2017 • 134
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Paper • 2205.14135 • Published May 27, 2022 • 15
Efficient Memory Management for Large Language Model Serving with PagedAttention

Paper • 2309.06180 • Published Sep 12, 2023 • 64
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Paper • 2307.08691 • Published Jul 17, 2023 • 9

QAT quality at honest 4-bit size for Apple Silicon: uniform 4-bit g64 MLX builds, no silent 8-bit upgrades. Yooz Labs (yooz.live).

YoozLabs/gemma-4-E4B-it-qat-lean-4bit-mlx

Text Generation • 1B • Updated 17 days ago • 192
YoozLabs/gemma-4-12B-it-qat-lean-4bit-mlx

Text Generation • 12B • Updated 17 days ago • 269
YoozLabs/Qwen3.5-0.8B-qat-lean-4bit-mlx

Text Generation • 0.1B • Updated 7 days ago • 129
YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx

Text Generation • 0.7B • Updated 7 days ago • 171

Autonomous Vehicles

HugoHE/faster-rcnn-bdd-finetune

Object Detection • Updated Jun 30, 2025 • 2
ThankGod/mapillary_traffic_sign_dataset_recommended

Viewer • Updated Apr 6, 2025 • 26k • 163

Uncensored local models

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 8 days ago • 12.4M • • 3.4k

Sleeping

1

Edutrack Backend

📚

1

MIUProject/VNCCS_PoseLibrary_Main

Updated May 23

Attention Is All You Need

Paper • 1706.03762 • Published Jun 12, 2017 • 134
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness

Paper • 2205.14135 • Published May 27, 2022 • 15
Efficient Memory Management for Large Language Model Serving with PagedAttention

Paper • 2309.06180 • Published Sep 12, 2023 • 64
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Paper • 2307.08691 • Published Jul 17, 2023 • 9

Running on Zero

MCP

2.1k

Wan2.2 14B Fast Preview

🐌

2.1k

generate a video from an image with a text prompt
Running on Zero

MCP

Featured

3.36k

Wan2.2 14B Fast

🎥

3.36k

generate a video from an image with a text prompt
Running on CPU Upgrade

Agents

2.24k

Omni Image Editor

🖼

2.24k

Image edit, text to image, image upscale, remove watermark

QAT quality at honest 4-bit size for Apple Silicon: uniform 4-bit g64 MLX builds, no silent 8-bit upgrades. Yooz Labs (yooz.live).

YoozLabs/gemma-4-E4B-it-qat-lean-4bit-mlx

Text Generation • 1B • Updated 17 days ago • 192
YoozLabs/gemma-4-12B-it-qat-lean-4bit-mlx

Text Generation • 12B • Updated 17 days ago • 269
YoozLabs/Qwen3.5-0.8B-qat-lean-4bit-mlx

Text Generation • 0.1B • Updated 7 days ago • 129
YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx

Text Generation • 0.7B • Updated 7 days ago • 171

PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation

Paper • 2607.02515 • Published 27 days ago • 19

Autonomous Vehicles

HugoHE/faster-rcnn-bdd-finetune

Object Detection • Updated Jun 30, 2025 • 2
ThankGod/mapillary_traffic_sign_dataset_recommended

Viewer • Updated Apr 6, 2025 • 26k • 163

deepreinforce-ai/Ornith-1.0-9B-GGUF

Text Generation • 9B • Updated Jun 25 • 4.07M • 576
Jackrong/Qwen3.5-9B-DeepSeek-V4-Flash-GGUF

Image-Text-to-Text • 9B • Updated 24 days ago • 90k • 286
DJLougen/Qwable-5-27B-Coder

Text Generation • 28B • Updated Jun 23 • 359 • • 42
DJLougen/Qwable-5-27B-Coder-GGUF

Text Generation • 27B • Updated Jun 23 • 9.43k • 16

Uncensored local models

google/gemma-4-31B-it

Image-Text-to-Text • 33B • Updated 8 days ago • 12.4M • • 3.4k

Bitcoin-Anchored Provenance

Prove a record existed before a given Bitcoin block, verifiable offline with no operator in the trust path. Existence and ordering only.

MarkovianProtocol/bitcoin-anchored-ai-provenance

Viewer • Updated 3 days ago • 151 • 98
Running

MCP

Markovian Provenance

⚛

AI-output provenance, verifiable against Bitcoin. No trust.
Runtime error

Agents

canoncheck

🔁

Cross-language canonical JSON + sha256/keccak256 (RFC 8785)

Sleeping

1

Edutrack Backend

📚

1

Previous
1
...
470
471
472
473
474
...
22,100
Next

Company

TOS Privacy About Careers

Website

Models Datasets Spaces Pricing Docs