Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • 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
Lukas Kremla's picture

Lukas Kremla

lukaskremla
3 1
chchewy's profile picture scoobysneck's profile picture YuzerAi's profile picture
·
  • lukaskremla
  • lukaskremla

AI & ML interests

None yet

Recent Activity

new activity 2 days ago
lukaskremla/Qwen3.8-27B-4bit-MLX-TextOnly:Reproducible adjacent-record isolation regression with Qwen3.8-27B-4bit-MLX-TextOnly on M1 Pro 32 GB
new activity 10 days ago
nex-agi/Nex-N2.5-Pro:Are the weights not meant to be released?
new activity 20 days ago
lukaskremla/Qwen3.8-27B-4bit-MLX-TextOnly:How much difference in token generation can we expect on a 24gb Mac pro?
View all activity

Organizations

None yet

New activity in lukaskremla/Qwen3.8-27B-4bit-MLX-TextOnly 2 days ago

Reproducible adjacent-record isolation regression with Qwen3.8-27B-4bit-MLX-TextOnly on M1 Pro 32 GB

1
#2 opened 2 days ago by
claymoretastic
New activity in nex-agi/Nex-N2.5-Pro 10 days ago

Are the weights not meant to be released?

4
#1 opened 13 days ago by
lukaskremla
New activity in lukaskremla/Qwen3.8-27B-4bit-MLX-TextOnly 20 days ago

How much difference in token generation can we expect on a 24gb Mac pro?

2
#1 opened about 1 month ago by
Py528
New activity in lukaskremla/Qwen3.8-27B-4bit-MLX-TextOnly about 1 month ago

How much difference in token generation can we expect on a 24gb Mac pro?

2
#1 opened about 1 month ago by
Py528
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs