Felix Hesse

Blackbeard82's activity

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

New activity in Aleph-Alpha/Kolibri-1 4 days ago

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

👍 10

6

#1 opened 5 days ago by

Blackbeard82

New activity in velaia/Kolibri-1-MLX-2bit 4 days ago

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

#1 opened 4 days ago by

Blackbeard82

New activity in AtomicChat/Qwen3.8-Flash-Next-GGUF about 1 month ago

Linear speed degradation correlated with context length

3

#13 opened about 1 month ago by

attention1

it works great on M1 Max 64GB

🔥 4

4

#5 opened about 1 month ago by

grokked-it

MTP

5

#6 opened about 1 month ago by

thiagottjv

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

👍 4

5

#12 opened about 1 month ago by

aydintb