Carlos Caaza

caaza's activity

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

upvoted a paper about 2 hours ago

PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models

Paper • 2602.06053 • Published Jan 14 • 5

reacted to danielhanchen's post with 🔥 about 2 hours ago

view post

Post

4844

You can now run MiniMax-2.5 locally! 🚀
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.

Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF

See translation

• 
• 

• 
• 1 reply

·

🔥

18

18

+

Reply

liked a Space 7 days ago

Running on A100

Featured

400

ACE-Step v1.5

🎵

400

Music Generation Foundation Model v1.5

upvoted a paper 7 days ago

LongVideoAgent: Multi-Agent Reasoning with Long Videos

Paper • 2512.20618 • Published Dec 23, 2025 • 55

liked a Space 7 days ago

Running

Featured

4.72k

Wan2.2 Animate

👁

4.72k

Wan2.2 Animate

liked a dataset 7 days ago

common-pile/caselaw_access_project

Viewer • Updated Jun 6, 2025 • 5.52M • 771 • 206

liked a model 7 days ago

tencent/HunyuanVideo-1.5

Text-to-Video • Updated Dec 25, 2025 • 23.8k • • 570

upvoted an article 7 days ago

view article

Article

PromptRL: Prompt Matters in RL for Flow-Based Image Generation

• 

14 days ago

•

3

upvoted an article 2 months ago

view article

Article

We Got Claude to Fine-Tune an Open Source LLM

• 
• 

Dec 4, 2025

•

593

liked a dataset 2 months ago

Anthropic/AnthropicInterviewer

Viewer • Updated Jan 6 • 1.25k • 552 • 358

liked a Space 2 months ago

Running

8

Jupyter Agent 2

🏃

8

Execute coding tasks and generate Jupyter notebooks automatically

liked a model 2 months ago

unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF

Text Generation • 31B • Updated 17 days ago • 164k • 470

liked a Space 2 months ago

Running

165

DeepFilterNet2

💩

165

Denoise your recordings and view spectrograms

liked a Space 3 months ago

Running on Zero

Featured

681

FLUX.2 [dev]

💻

681

Create and edit images from prompts and optional photos

liked 6 models 3 months ago

black-forest-labs/FLUX.2-dev

Image-to-Image • Updated Nov 27, 2025 • 164k • • 1.37k

deepseek-ai/DeepSeek-V3.2

Text Generation • 685B • Updated Dec 1, 2025 • 346k • • 1.25k

Qwen/Qwen3-Omni-30B-A3B-Instruct

Any-to-Any • 35B • Updated Sep 22, 2025 • 736k • 847

Alpha-VLLM/Lumina-mGPT-34B-512

Any-to-Any • 34B • Updated Dec 12, 2024 • 9 • 3

Alpha-VLLM/Lumina-mGPT-7B-768-Omni

Any-to-Any • 7B • Updated Dec 12, 2024 • 22 • 9

Alpha-VLLM/Lumina-mGPT-7B-512-MultiImage

Any-to-Any • 7B • Updated Dec 12, 2024 • 89 • 5