Alexandre Strube

surak's activity

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

New activity in NousResearch/Arete-27B 1 day ago

HyperArete: calibrated W4A16 checkpoint and HyperQwen recipe for a 24 GB GPU

#19 opened 1 day ago by

surak

updated a model 1 day ago

surak/HyperArete-27B-W4A16

Image-Text-to-Text • 6B • Updated 1 day ago • 24

published a model 1 day ago

surak/HyperArete-27B-W4A16

Image-Text-to-Text • 6B • Updated 1 day ago • 24

liked a model 3 months ago

Qwen/Qwen3.8-27B

Image-Text-to-Text • 28B • Updated 3 days ago • 7.51M • • 19.5k

liked a model 4 months ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated Sep 2 • 742k • • 12k

New activity in MiniMaxAI/MiniMax-M2 about 1 year ago

Why does it keep trying to connect to huggingface?

1

#16 opened about 1 year ago by

surak

upvoted a paper about 1 year ago

Optimal Scaling Needs Optimal Norm

Paper • 2510.03871 • Published Oct 4, 2025 • 30

New activity in openai/gpt-oss-120b over 1 year ago

Can gpt-oss support local vllm deployment on a100 GPU?

10

#73 opened over 1 year ago by

Cola-any

upvoted a collection over 1 year ago

🌸 April 2025 - Open releases from the Chinese community

Collection

40 items • Updated Jan 9 • 13

New activity in google/gemma-3-12b-it-qat-q4_0-gguf over 1 year ago

Exception "general.name" occurs

5

#5 opened over 1 year ago by

hudson5

New activity in deepseek-ai/DeepSeek-V3 almost 2 years ago

minimum vram?

👍 1

11

#9 opened almost 2 years ago by

CHNtentes

New activity in mistralai/Ministral-8B-Instruct-2410 about 2 years ago

It does not like to run local with the latest VLLM and transformers:

5

#6 opened about 2 years ago by

surak

New activity in tiiuae/falcon-mamba-7b about 2 years ago

AttributeError: 'FalconMambaCausalLMOutput' object has no attribute 'past_key_values'

6

#12 opened about 2 years ago by

surak

New activity in TheBloke/guanaco-65B-HF over 3 years ago

Can't run model

5

#1 opened over 3 years ago by

mikeytrw

liked a model almost 4 years ago

google/switch-c-2048

Updated Jan 11, 2024 • 524 • 311