Tianyi Zhang

LeanQuant

·

AI & ML interests

None yet

Recent Activity

updated a model about 22 hours ago

QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4

published a model about 22 hours ago

QUASAR-QAT/Qwen3.8-27B-QUASAR-NVFP4

updated a model 5 days ago

LeanQuant/quasar-qwen3.8-27b-all

View all activity

Organizations

Posts 1

Post

437

🚀 Full-Quality Wan2.2 Video Generation on a single 24GB GPU — Powered by DFloat11

We just released the DFloat11 compressed Wan2.2 models. Now you can run full-quality Wan2.2 video generation on a single 24GB GPU, thanks to DFloat11 compression and CPU offloading.

🔗 Image-to-Video: DFloat11/Wan2.2-I2V-A14B-DF11
🔗 Text-to-Video: DFloat11/Wan2.2-T2V-A14B-DF11

Articles 1

Article

2

Wan2.1 + DFloat11 Enables High-quality Text-to-video With 24GB VRAM

Papers 1

arxiv:2504.11651

models 25

LeanQuant/quasar-qwen3.8-27b-all

27B • Updated 5 days ago • 17

LeanQuant/quasar-qwen3.8-27b

27B • Updated 7 days ago • 417

LeanQuant/Qwen-QAT-NVFP4-checkpoints

Updated 24 days ago

LeanQuant/SketchTune-ckpts

Updated Jun 29, 2025 • 3

LeanQuant/SketchTune

Updated Jun 24, 2025 • 7 • 1

LeanQuant/Meta-Llama-3-8B-nu-4bit

Text Generation • 5B • Updated Feb 25, 2025 • 5

LeanQuant/Llama-2-13b-nu-3bit

Text Generation • 7B • Updated Feb 25, 2025 • 9

LeanQuant/Meta-Llama-3-8B-nu-2bit

Text Generation • 5B • Updated Feb 25, 2025 • 6

LeanQuant/Meta-Llama-3-8B-nu-3bit

Text Generation • 5B • Updated Feb 25, 2025 • 8

LeanQuant/Mistral-7B-v0.1-nu-4bit

Text Generation • 4B • Updated Feb 25, 2025 • 6

datasets 0

None public yet