🔄 In a Training Loop

Andy Chen

andynoodles

14 1 34

yi-hsiang-chen-tw

AI & ML interests

Feel free to contact me through Linkedin

Recent Activity

upvoted a paper 6 days ago

Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards

repliedto onekq's post 11 days ago

My take on device-side inference: it's all about high bandwidth memory (thinking about it, this holds for the cloud too). MacBooks enjoy incidental capacity of apple silicon, but per-device RAM is too low (16 to 24GB), only sufficient for a decent SLM. 512GB is the highest you can go (Kimi K2*). Counting MLX downloads of Kimi K2* on Huggingface, I estimate the user base to be <25K. On the other hand, the newly debuted DGX station (Nvidia) has 748GB, which can fit in the latest Kimi, DS, and Qwen. Also the quantization options of CUDA is way better than MLX. For high-end inferencing, I place my bet on workstations over Macs.

liked a model 11 days ago

zai-org/GLM-5.3

View all activity

Organizations

liked 3 models 11 days ago

liked 2 models 16 days ago

nvidia/Nemotron-3-Embed-1B-BF16

google/timesfm-3.0-pytorch

Time Series Forecasting • 0.3B • Updated 11 days ago • 798k • 768

liked 2 models 18 days ago

Inferact/Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text • 118B • Updated 18 days ago • 74.5k • 25

Qwen/Qwen3.8-Flash-Next

Image-Text-to-Text • 180B • Updated 17 days ago • 624k • 5.15k

liked 4 models about 1 month ago

Inferact/Kimi-K3-DSpark

Text Generation • 4B • Updated Jul 29 • 20.9k • 55

OpenMOSS-Team/MOSS-Transcribe-Diarize

Audio-Text-to-Text • 0.9B • Updated 11 days ago • 219k • 428

MiniMaxAI/MiniMax-H3

Image-Text-to-Video • 33B • Updated Aug 13 • 4.82M • • 5.22k

deepseek-ai/DeepSeek-V4-Flash-0731

Text Generation • 304B • Updated Aug 1 • 4.38M • • 3.94k

liked 3 models about 2 months ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 11 days ago • 2.21M • • 11.3k

poolside/Laguna-S-2.1-NVFP4

Text Generation • 118B • Updated 19 days ago • 462k • 191

Lightricks/LTX-Video

Image-to-Video • 2B • Updated Jul 16, 2025 • 751k • 2.3k

liked 3 models 2 months ago

nvidia/llama-nemotron-embed-1b-v2

Feature Extraction • 1B • Updated May 20 • 470k • 63

nvidia/nemotron-ocr-v2

Image-to-Text • Updated May 22 • 887 • 256

openai/privacy-filter

Token Classification • 1B • Updated Apr 22 • 274k • • 1.75k

liked 2 datasets 3 months ago

HuggingFaceFW/ocr-annotations

Viewer • Updated Oct 20, 2025 • 1.62k • 92 • 19

HuggingFaceFW/fineweb

Viewer • Updated Jul 11, 2025 • 52.5B • 370k • 3.31k

liked a model 3 months ago

lightx2v/Qwen-Image-Edit-2511-Lightning

Image-to-Image • Updated Jan 15 • 370k • • 525

Andy Chen

AI & ML interests

Recent Activity

Organizations

andynoodles's activity