Hongyu Shi

HongyuS's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 2 days ago

Qwen3.8

Collection

Qwen3.8 Unsloth quants including Qwen3.8-27B! Run and train Qwen3.8 with the Unsloth Desktop app. • 7 items • Updated about 3 hours ago • 59

liked a model 16 days ago

deepseek-ai/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated 19 days ago • 2.33M • • 3.56k

liked 3 models about 2 months ago

deepseek-ai/DeepSeek-V4-Pro-DSpark

Text Generation • 1.7T • Updated Jul 4 • 20.6k • 541

deepseek-ai/DeepSeek-V4-Flash-DSpark

Text Generation • 165B • Updated Jul 4 • 488k • 259

baidu/Unlimited-OCR

Image-Text-to-Text • 3B • Updated 22 days ago • 3.24M • 4.08k

liked 3 models 2 months ago

mlx-community/gemma-4-26B-A4B-it-qat-4bit

Image-Text-to-Text • 5B • Updated Jun 5 • 2.53k • 4

mlx-community/gemma-4-31B-it-qat-4bit

Image-Text-to-Text • 8B • Updated Jun 5 • 1.56k • 3

mlx-community/gemma-4-12B-it-qat-4bit

Image-Text-to-Text • 3B • Updated Jun 5 • 23.2k • 25

liked a model 3 months ago

anemll/DeepSeek-V4-Flash-FP4-FP8-SSD

Text Generation • 7B • Updated Apr 29 • 197 • 8

liked 3 models 4 months ago

deepseek-ai/DeepSeek-V4-Flash

Text Generation • 291B • Updated Jun 22 • 1.89M • • 2.12k

deepseek-ai/DeepSeek-V4-Pro

Text Generation • 1.6T • Updated Jun 22 • 1.22M • • 5.46k

circlestone-labs/Anima

Updated 26 days ago • 819k • 2.1k

upvoted an article 4 months ago

view article

Article

Continuous batching from first principles

• 
• 
• +1

ror, ArthurZ, mcpotato

•

Nov 25, 2025

• 434

upvoted a collection 4 months ago

DFlash

Collection

Block Diffusion for Flash Speculative Decoding • 23 items • Updated Jun 28 • 154

liked a model 4 months ago

Lightricks/LTX-2.3

Image-to-Video • Updated 4 days ago • 1.63M • 1.83k

liked 2 models 5 months ago

FakeRockert543/gemma-4-31b-it-MLX-8bit

Image-Text-to-Text • 10B • Updated Apr 3 • 36 • 2

Brooooooklyn/Qwen3.5-27B-UD-Q5_K_XL-mlx

Text Generation • 8B • Updated Mar 29 • 28 • 1

upvoted a collection 5 months ago

Qwen-3.5-unsloth-mlx

Collection

AWQ-style pre-scaling using Unsloth's imatrix calibration data, then 3-6-bit affine quantization with the Unsloth mixed-precision recipe via MLX • 20 items • Updated Mar 29 • 20

liked a dataset 6 months ago

peteromallet/dataclaw-peteromallet

Viewer • Updated Feb 25 • 549 • 195 • 300

liked a model 6 months ago

Qwen/Qwen3.5-122B-A10B

Image-Text-to-Text • 125B • Updated Apr 24 • 2.16M • • 609