Kir Belevich

deepsweet's activity

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

updated a model about 4 hours ago

deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8

Text Generation • 10B • Updated about 4 hours ago

published a model about 6 hours ago

deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8

Text Generation • 10B • Updated about 4 hours ago

updated 8 models about 10 hours ago

deepsweet/Qwen3.6-35B-A3B-MLX-oQ4

Text Generation • 6B • Updated about 10 hours ago • 1.13k

deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ4-FP16

Text Generation • 6B • Updated about 10 hours ago • 257

deepsweet/Qwen3.6-35B-A3B-MLX-oQ4-FP16

Text Generation • 6B • Updated about 10 hours ago • 2.71k

deepsweet/Qwen3.6-35B-A3B-MLX-oQ5

Text Generation • 7B • Updated about 10 hours ago • 527

deepsweet/Qwen3.6-35B-A3B-MLX-oQ5-FP16

Text Generation • 7B • Updated about 10 hours ago • 1.68k

deepsweet/Qwen3.6-35B-A3B-MLX-oQ8

Text Generation • 10B • Updated about 10 hours ago • 1.76k • 2

deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8-FP16

Text Generation • 10B • Updated about 10 hours ago • 608

deepsweet/Qwen3.6-35B-A3B-MLX-oQ8-FP16

Text Generation • 10B • Updated about 10 hours ago • 4.86k • 2

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8-FP16 about 17 hours ago

M1 Ultra 64GB FP16 improvements

9

#1 opened 1 day ago by

KnucklesXBT

updated a model about 17 hours ago

deepsweet/Qwen3.6-27B-MLX-oQ8-FP16

Text Generation • 8B • Updated about 17 hours ago

updated a collection about 18 hours ago

Qwen3.6

Collection

12 items • Updated about 18 hours ago

published a model about 18 hours ago

deepsweet/Qwen3.6-27B-MLX-oQ8-FP16

Text Generation • 8B • Updated about 17 hours ago

updated a model about 18 hours ago

deepsweet/Qwen3.6-27B-MLX-oQ5-FP16

Text Generation • 5B • Updated about 18 hours ago

published a model about 19 hours ago

deepsweet/Qwen3.6-27B-MLX-oQ5-FP16

Text Generation • 5B • Updated about 18 hours ago

upvoted an article about 19 hours ago

view article

Article

Why Maybe We're Measuring LLM Compression Wrong

• 

Jun 21, 2025

•

16

New activity in deepsweet/Qwen3.6-35B-A3B-MLX-VLM-oQ8-FP16 about 20 hours ago

non FP16 : M3+ version of VLM

1

#2 opened about 20 hours ago by

jeromelaurens