Stanislav Ursache

itsthenewmeta's activity

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

liked a model 3 days ago

magibu/magibu-11b-v0.8

Image-Text-to-Text • 12B • Updated 3 days ago • 277 • 11

liked a model 4 days ago

PrimeIntellect/INTELLECT-3.1

Text Generation • 107B • Updated 4 days ago • 297 • 33

reacted to danielhanchen's post with 🔥 4 days ago

view post

Post

5514

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

liked a model 4 days ago

Qwen/Qwen3-Coder-Next

Text Generation • Updated 18 days ago • 415k • • 944

upvoted a collection 6 days ago

Qwen3.5

Collection

Qwen3.5 is Qwen's new model family including Qwen3.5-397B-A17B. • 2 items • Updated 6 days ago • 8

liked a model 6 days ago

Qwen/Qwen3.5-397B-A17B

Image-Text-to-Text • Updated 2 days ago • 133k • • 833

reacted to Ujjwal-Tyagi's post with 🔥 9 days ago

view post

Post

2980

GLM 5 is insane, it ranks #4 Globally!

See translation

• 

• 
• 
• 
• 4 replies

·

🔥

10

10

🤯

2

2

+

Reply

upvoted a collection 13 days ago

Qwen3-Next

Collection

4 items • Updated Dec 31, 2025 • 184

liked 3 models 17 days ago

ACE-Step/Ace-Step1.5

Text-to-Audio • Updated 19 days ago • 45.3k • 587

ACE-Step/acestep-v15-base

Text-to-Audio • 2B • Updated 16 days ago • 7.1k • 50

unsloth/Qwen3-Coder-Next-GGUF

Text Generation • 80B • Updated 4 days ago • 469k • 379

liked a model 20 days ago

circlestone-labs/Anima

Updated 21 days ago • 174k • 654

liked a model 24 days ago

Qwen/Qwen3-ASR-1.7B

Automatic Speech Recognition • Updated 23 days ago • 423k • 515

reacted to danielhanchen's post with 🚀 25 days ago

view post

Post

3421

You can now run Kimi K2.5 locally! 🔥

We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.

GGUF: unsloth/Kimi-K2.5-GGUF

Guide: https://unsloth.ai/docs/models/kimi-k2.5

See translation

• 
• 

• 
• 
• 
• 7 replies

·

🚀

16

16

😎

3

3

🔥

2

2

👀

1

1

+

Reply

liked a model 25 days ago

Tongyi-MAI/Z-Image

Text-to-Image • Updated 25 days ago • 31.9k • • 932

liked a model 29 days ago

google/translategemma-27b-it

Image-Text-to-Text • Updated 24 days ago • 18.9k • 318

liked 4 models about 1 month ago

mistralai/Magistral-Small-2509

Updated Dec 2, 2025 • 6.66k • 284

unsloth/GLM-4.7-Flash-GGUF

Text Generation • 30B • Updated 9 days ago • 360k • 508

zai-org/GLM-4.7-Flash

Text Generation • Updated 24 days ago • 1.75M • • 1.55k

google/medgemma-1.5-4b-it

Image-Text-to-Text • Updated 29 days ago • 142k • 474