Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
Rafael Sobek's picture

Rafael Sobek

rafaelsobek
2 2
localllmrig's profile picture
·
https://accelerando.company

AI & ML interests

None yet

Recent Activity

new activity about 15 hours ago
thinkingmachines/Inkling-2-Mini:Multi-GPU llama.cpp benchmarks — 2× RTX 5060 Ti 16GB: pp/tg ladder, max context up to 393k, parallel tests up to 64k (UD-Q4_K_XL)
new activity 3 days ago
maxwell-model/Maxwell-V1-Flash:First benchmarks: pp512/tg128 on 2× RTX 5060 Ti 16GB (AD-Q5_K-Q4_K, tensor-parallel, 8k→128k)
liked a model 3 days ago
rafaelsobek/Qwen3.8-27B-NVFP4-GGUF
View all activity

Organizations

None yet

New activity in thinkingmachines/Inkling-2-Mini about 15 hours ago

Multi-GPU llama.cpp benchmarks — 2× RTX 5060 Ti 16GB: pp/tg ladder, max context up to 393k, parallel tests up to 64k (UD-Q4_K_XL)

#24 opened about 15 hours ago by
rafaelsobek
New activity in maxwell-model/Maxwell-V1-Flash 3 days ago

First benchmarks: pp512/tg128 on 2× RTX 5060 Ti 16GB (AD-Q5_K-Q4_K, tensor-parallel, 8k→128k)

👍 1
#6 opened 3 days ago by
rafaelsobek
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs