1 4 246

Carsten Li

carstenli

AI & ML interests

None yet

Recent Activity

liked a model about 12 hours ago

Qwen/Qwen2.5-VL-3B-Instruct

liked a Space 12 days ago

primecai/diffusion-self-distillation

liked a Space 15 days ago

THUDM-HF-SPACE/CogView4

View all activity

Organizations

None yet

carstenli's activity

liked a model about 12 hours ago

Qwen/Qwen2.5-VL-3B-Instruct

Image-Text-to-Text • Updated Feb 15 • 1.04M • 273

liked a Space 12 days ago

184

Diffusion Self Distillation

🦀

Tuning-free subject-driven generation

liked a Space 15 days ago

101

CogView4

🖌

Gradio demo of CogView4-6B

liked a model 15 days ago

THUDM/CogView4-6B

Text-to-Image • Updated 8 days ago • 36.5k • • 200

liked a model 16 days ago

wangfuyun/PCM_Weights

Text-to-Image • Updated Oct 30, 2024 • 71 • 89

reacted to ngxson's post with 🚀 19 days ago

Post

3082

A comprehensive matrix for which format should you use.

Read more on my blog post: https://huggingface.co/blog/ngxson/common-ai-model-formats

| Hardware        | GGUF      | PyTorch                | Safetensors              | ONNX  |
|-----------------|-----------|------------------------|--------------------------|-------|
| CPU             | ✅ (best) | 🟡                      | 🟡                       | ✅    |
| GPU             | ✅        | ✅                      | ✅                       | ✅    |
| Mobile          | ✅        | 🟡 (via executorch)     | ❌                       | ✅    |
| Apple silicon   | ✅        | 🟡                      | ✅ (via MLX framework)   | ✅    |