adonishong

adonishong's activity

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

New activity in QuantTrio/GLM-4.5-GPTQ-Int4-Int8Mix 4 days ago

Does it possible to create a version without MTP layer to save some VRAM

#1 opened 4 days ago by

adonishong

New activity in QuantTrio/GLM-4.5-AWQ 4 days ago

Does it possible to create a version without MTP layer to save some VRAM

👍 1

#3 opened 4 days ago by

adonishong

New activity in mlx-community/Kimi-VL-A3B-Thinking-8bit about 1 month ago

looking forward upgrading to kimi-vl-a3b-thinking-2506

#1 opened about 1 month ago by

adonishong

New activity in mlx-community/Llama-4-Scout-17B-16E-Instruct-4bit 4 months ago

Llama 4 not working with MLX VLM?

1

#2 opened 4 months ago by

leadangle

New activity in deepseek-ai/DeepSeek-V3 7 months ago

Please make V3-lite

❤️ 👍 50

4

#12 opened 7 months ago by

rombodawg

How can we thank you enough, whale bros?

❤️ 👍 56

10

#1 opened 7 months ago by

KrishnaKaasyap

New activity in Skywork/Skywork-MoE-Base about 1 year ago

vram requirements?

1

#2 opened about 1 year ago by

joujiboi

New activity in deepseek-ai/DeepSeek-V2-Chat about 1 year ago

Ollama support

👍 1

1

#9 opened about 1 year ago by

Dao3

liked a model about 1 year ago

deepseek-ai/DeepSeek-V2-Lite-Chat

Text Generation • 16B • Updated Jun 25, 2024 • 109k • 125