Flavio Catalani

fakezeta's activity

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

liked a model 15 days ago

noctrex/LFM2-24B-A2B-MXFP4_MOE-GGUF

Text Generation • 24B • Updated 14 days ago • 1.08k • 9

upvoted a collection 15 days ago

Qwen3.5

Collection

21 items • Updated 2 days ago • 1.1k

liked 2 models about 1 month ago

RuneXX/LTX-2-Workflows

Updated 6 days ago • 271

MachineDelusions/LTX-2_Image2Video_Adapter_LoRa

Updated Jan 26 • 139

liked a model about 2 months ago

Wildminder/AI-windows-whl

Updated 17 days ago • 110

upvoted an article 2 months ago

view article

Article

EuroLLM-22B

• 

Dec 14, 2025

•

48

liked 2 models 5 months ago

yairpatch/Qwen3-VL-30B-A3B-Instruct-GGUF

Updated Oct 27, 2025 • 8 • 25

yairpatch/Qwen3-VL-30B-A3B-Thinking-GGUF

Updated Oct 27, 2025 • 24 • 29

reacted to lysandre's post with 🚀 6 months ago

view post

Post

8138

We're kick-starting the process of Transformers v5, with @ArthurZ and @cyrilvallez !

v5 should be significant: we're using it as a milestone for performance optimizations, saner defaults, and a much cleaner code base worthy of 2025.

Fun fact: v4.0.0-rc-1 came out on Nov 19, 2020, nearly five years ago!

See translation

• 

• 
• 
• 6 replies

·

🚀

19

19

👍

9

9

🔥

6

6

+

Reply

updated a Space 6 months ago

Sleeping

Romeintransit

🏆

Display transit information for Rome

liked a model 6 months ago

cartesia/azzurra-voice

Text-to-Speech • 2B • Updated 27 days ago • 2.19k • 13

liked a model 8 months ago

city96/umt5-xxl-encoder-gguf

6B • Updated Mar 4, 2025 • 92.4k • 146

liked a model 9 months ago

mistralai/Mistral-Small-3.2-24B-Instruct-2506

Updated Dec 22, 2025 • 304k • 568

reacted to cbensimon's post with 🔥 10 months ago

view post

Post

6137

🚀 ZeroGPU medium size is now available as a power-user feature

Nothing too fancy for now—ZeroGPU Spaces still default to large (70GB VRAM)—but this paves the way for:
- 💰 size-based quotas / pricing (medium will offer significantly more usage than large)
- 🦣 the upcoming xlarge size (141GB VRAM)

You can as of now control GPU size via a Space variable. Accepted values:
- auto (future default)
- medium
- large (current default)

The auto mode checks total CUDA tensor size during startup:
- More than 30GB → large
- Otherwise → medium

See translation

• 

• 
• 
• 
• 3 replies

·

🔥

25

25

👀

5

5

🚀

4

4

🤗

4

4

👍

4

4

+

Reply

updated a model 10 months ago

fakezeta/amoral-Qwen3-4B-openvino

Text Generation • Updated May 15, 2025 • 3

published a model 10 months ago

fakezeta/amoral-Qwen3-4B-openvino

Text Generation • Updated May 15, 2025 • 3

published a Space 10 months ago

Sleeping

Romeintransit

🏆

Display transit information for Rome

New activity in unsloth/Qwen3-30B-A3B-GGUF 10 months ago

Please quantize a Q5_K_S version

👍 1

3

#9 opened 10 months ago by

fakezeta

updated 2 models 10 months ago

fakezeta/amoral-Qwen3-4B

Text Generation • 4B • Updated May 11, 2025 • 4 • 2

fakezeta/amoral-Qwen3-4B-GGUF

4B • Updated May 9, 2025 • 31