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
Felix Hesse's picture

Felix Hesse

Blackbeard82
6 1

AI & ML interests

None yet

Recent Activity

new activity about 2 months ago
Aleph-Alpha/Kolibri-1:Request: Quantized versions (MLX / GGUF) for Apple Silicon – happy to benchmark
new activity about 2 months ago
velaia/Kolibri-1-MLX-2bit:Kolibri-1 2-bit on an M2 Max (64 GB): multi-session throughput and a KV-cache pitfall in mlx-lm
new activity about 2 months ago
Aleph-Alpha/Kolibri-1:Request: Quantized versions (MLX / GGUF) for Apple Silicon – happy to benchmark
View all activity

Organizations

None yet

New activity in Aleph-Alpha/Kolibri-1 about 2 months ago

Request: Quantized versions (MLX / GGUF) for Apple Silicon – happy to benchmark

👍 10
6
#1 opened about 2 months ago by
Blackbeard82
New activity in velaia/Kolibri-1-MLX-2bit about 2 months ago

Kolibri-1 2-bit on an M2 Max (64 GB): multi-session throughput and a KV-cache pitfall in mlx-lm

❤️ 1
#1 opened about 2 months ago by
Blackbeard82
New activity in AtomicChat/Qwen3.8-Flash-Next-GGUF 3 months ago

Linear speed degradation correlated with context length

3
#13 opened 3 months ago by
attention1

it works great on M1 Max 64GB

🔥 4
4
#5 opened 3 months ago by
grokked-it

MTP

5
#6 opened 3 months ago by
thiagottjv

MTP support for AtomicChat Qwen3.8-Flash-Next GGUF

👍 4
5
#12 opened 3 months ago by
aydintb
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs