Manan Shah

Manan1717

AI & ML interests

None yet

Recent Activity

new activity 7 days ago

unsloth/Qwen3.6-27B-UD-MLX-3bit:Quick question: I noticed your MLX 3-bit variant sits at ~24GB, while GGUF’s Q3_K_S is only ~12.4GB?

new activity 7 days ago

unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit:generation_config.json is missing

liked a model 11 days ago

unsloth/Qwen3.6-27B-MLX-8bit

View all activity

Organizations

New activity in unsloth/Qwen3.6-27B-UD-MLX-3bit 7 days ago

Quick question: I noticed your MLX 3-bit variant sits at ~24GB, while GGUF’s Q3_K_S is only ~12.4GB?

👀 1

#1 opened 10 days ago by

realperson1234

New activity in unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit 7 days ago

generation_config.json is missing

#3 opened 9 days ago by

l2dy

liked 3 models 11 days ago

NameError: name 'tree_reduce' is not defined

#1 opened 13 days ago by

datatap

New activity in unsloth/Kimi-K2.6-GGUF 12 days ago

Will other quants be available?

❤️ 6

#3 opened 13 days ago by

x-polyglot-x

upvoted a collection 13 days ago

Qwen3.6

Collection

13 items • Updated 11 days ago • 35

liked 2 models 13 days ago

unsloth/Qwen3.6-35B-A3B-MLX-8bit

Image-Text-to-Text • 10B • Updated 17 days ago • 29.2k • 21

unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit

Image-Text-to-Text • 6B • Updated 14 days ago • 131k • 59

liked 2 models 28 days ago

unsloth/gemma-4-31b-it-UD-MLX-4bit

Image-Text-to-Text • 7B • Updated 21 days ago • 3.35k • 25

unsloth/gemma-4-26b-a4b-it-UD-MLX-4bit

Image-Text-to-Text • 5B • Updated 21 days ago • 2.59k • 25

liked 3 models about 1 month ago

unsloth/gemma-4-E2B-it-UD-MLX-4bit

Image-Text-to-Text • 1B • Updated 21 days ago • 2.6k • 18

unsloth/gemma-4-E2B-it-MLX-8bit

Image-Text-to-Text • 1B • Updated 21 days ago • 590 • 7

unsloth/gemma-4-26B-A4B-it-GGUF

Image-Text-to-Text • 25B • Updated 17 minutes ago • 3.38M • 657

liked a model about 2 months ago

unsloth/NVIDIA-Nemotron-3-Nano-4B

Text Generation • Updated Mar 26 • 19.4k • 13