tantk

tantk's activity

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

updated a model 3 days ago

tantk/Voxtral-4B-Realtime-VQF

Automatic Speech Recognition • Updated 3 days ago • 23

liked a model 3 days ago

Aratako/Irodori-TTS-500M

Text-to-Speech • 0.5B • Updated 10 days ago • 44

published a model 3 days ago

tantk/Voxtral-4B-Realtime-VQF

Automatic Speech Recognition • Updated 3 days ago • 23

upvoted a collection 4 days ago

Qwen3

Collection

84 items • Updated Dec 31, 2025 • 1.71k

liked a model 5 days ago

mistral-hackaton-2026/voxtral-sentinel-4b

Automatic Speech Recognition • 4B • Updated 6 days ago • 21 • 3

updated a Space 6 days ago

Sleeping

MeetingMind VectorDB

🔍

published a Space 6 days ago

Sleeping

MeetingMind VectorDB

🔍

updated a model 6 days ago

mistral-hackaton-2026/voxtral_model

Automatic Speech Recognition • Updated 6 days ago • 1

published a model 6 days ago

mistral-hackaton-2026/voxtral_model

Automatic Speech Recognition • Updated 6 days ago • 1

updated a model 7 days ago

tantk/gpu_endpoint

Automatic Speech Recognition • Updated 6 days ago

published a model 7 days ago

tantk/gpu_endpoint

Automatic Speech Recognition • Updated 6 days ago

updated a model 7 days ago

mistral-hackaton-2026/meetingmind-gpu

Audio Classification • Updated 7 days ago • 1

published a model 7 days ago

mistral-hackaton-2026/meetingmind-gpu

Audio Classification • Updated 7 days ago • 1

updated a Space 7 days ago

Sleeping

Make Meeting Analyses Great Again

🚀

Generate real-time meeting transcripts with speaker tags

published a Space 7 days ago

Sleeping

Make Meeting Analyses Great Again

🚀

Generate real-time meeting transcripts with speaker tags

reacted to danielhanchen's post with 🔥 18 days ago

view post

Post

5652

You can now run Qwen3.5 locally! 💜
Qwen3.5-397B-A17B is an open MoE vision reasoning LLM for agentic coding & chat. It performs on par with Gemini 3 Pro, Claude Opus 4.5 & GPT-5.2.

GGUF: unsloth/Qwen3.5-397B-A17B-GGUF
Run Dynamic 3-bit on a 192GB Mac for 20 tokens/s.

Guide: https://unsloth.ai/docs/models/qwen3.5

See translation

• 
• 

• 
• 
• 
• 9 replies

·

🔥

19

19

❤️

6

6

🚀

2

2

+

Reply

upvoted a collection 18 days ago

Tiny Aya

Collection

Bridging Scale and Multilingual Depth • 10 items • Updated 18 days ago • 64

New activity in tantk/Nanbeige4.1-3B-GGUF 22 days ago

Rest of Quantizations?

1

#1 opened 24 days ago by

henkey

q2 almost always goes in a recurring loop

1

#2 opened 22 days ago by

Pronkin

updated a model 22 days ago

tantk/Nanbeige4.1-3B-GGUF

4B • Updated 22 days ago • 12.4k • 5