mimeng1990

AI & ML interests

None yet

Recent Activity

new activity about 15 hours ago

zai-org/GLM-4.6:Will release Air version of GLM-4.6 today?

new activity 3 days ago

VibeStudio/MiniMax-M2-THRIFT-55-MLX-6bit:thanks a lot👍

new activity 4 days ago

introvoyz041/LIMI-Air-qx86-hi-mlx-mlx-4Bit:Are you sure this is 4-bit quantization? Is there a typo?

View all activity

Organizations

None yet

New activity in zai-org/GLM-4.6 about 15 hours ago

Will release Air version of GLM-4.6 today?

❤️ 5

#22 opened about 1 month ago by

mimeng1990

New activity in VibeStudio/MiniMax-M2-THRIFT-55-MLX-6bit 3 days ago

thanks a lot👍

#1 opened 3 days ago by

mimeng1990

New activity in introvoyz041/LIMI-Air-qx86-hi-mlx-mlx-4Bit 4 days ago

Are you sure this is 4-bit quantization? Is there a typo?

#1 opened 4 days ago by

mimeng1990

New activity in VibeStudio/MiniMax-M2-THRIFT-55-MLX-4bit 6 days ago

Could you please quantize a 6-bit or 6.5-bit model that requires 93-97GB of memory? Such a model could be deployed on a Mac with 128GB of RAM. Thank you very much!

#1 opened 6 days ago by

mimeng1990

New activity in nightmedia/LIMI-Air-qx86-hi-mlx about 1 month ago

👍👍👍

❤️ 👀 1

#3 opened about 1 month ago by

mimeng1990

New activity in mrtoots/TheDrummer-GLM-Steam-106B-A12B-v1-MLX-8Bit about 1 month ago

Hi, could you please release a Qx86 version? I'd like the size to be between 93GB and 97GB so it can be easily deployed on a 128GB Mac. Thank you so much!

#1 opened about 1 month ago by

mimeng1990

New activity in nightmedia/GLM-Steam-106B-A12B-v1-qx65g-hi-mlx about 1 month ago

thanks a lot

👍 ❤️ 2

#1 opened about 1 month ago by

mimeng1990

New activity in mlx-community/GLM-4.5-Air-bf16 about 1 month ago

Hi, could you please release a Qx86 version? I'd like the size to be between 93GB and 97GB so it can be easily deployed on a 128GB Mac. Thank you so much!

#1 opened about 1 month ago by

mimeng1990

New activity in Qwen/Qwen3-Next-80B-A3B-Thinking about 1 month ago

I hope qwen3 will open-source a large 120b model, like the GPT-120b. GPT's Chinese version isn't very good; we still need qwen.

👍 1

#16 opened about 1 month ago by

mimeng1990

New activity in nightmedia/GLM-4.5-Air-REAP-82B-A12B-qx64g-hi-mlx about 1 month ago

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

❤️ 1

#2 opened about 1 month ago by

mimeng1990

New activity in zerofata/GLM-4.5-Iceblink-106B-A12B about 1 month ago

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

#3 opened about 1 month ago by

mimeng1990

New activity in nightmedia/LIMI-Air-qx86-hi-mlx about 1 month ago

The LIMI-Air-qx86-hi-mlx model is 97GB in size and works very well when deployed locally on a Mac with 128GB of RAM.

🔥 1

#2 opened about 1 month ago by

mimeng1990

"model happier and more eager to explore and innovate"

🔥 ❤️ 1

#1 opened 2 months ago by

bobig

New activity in beezu/zerofata_GLM-4.5-Iceblink-106B-A12B-MLX-MXFP4 about 1 month ago

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

#1 opened about 1 month ago by

mimeng1990

New activity in nightmedia/GLM-4.5-Air-REAP-82B-A12B-qx64g-hi-mlx about 1 month ago

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

❤️ 1

#2 opened about 1 month ago by

mimeng1990

New activity in beezu/zerofata_GLM-4.5-Iceblink-106B-A12B-MLX-MXFP4 about 1 month ago

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

#1 opened about 1 month ago by

mimeng1990

mimeng1990

AI & ML interests

Recent Activity

Organizations

mimeng1990's activity

Will release Air version of GLM-4.6 today?

thanks a lot👍

Are you sure this is 4-bit quantization? Is there a typo?

Could you please quantize a 6-bit or 6.5-bit model that requires 93-97GB of memory? Such a model could be deployed on a Mac with 128GB of RAM. Thank you very much!

👍👍👍

Hi, could you please release a Qx86 version? I'd like the size to be between 93GB and 97GB so it can be easily deployed on a 128GB Mac. Thank you so much!

thanks a lot

Hi, could you please release a Qx86 version? I'd like the size to be between 93GB and 97GB so it can be easily deployed on a 128GB Mac. Thank you so much!

I hope qwen3 will open-source a large 120b model, like the GPT-120b. GPT's Chinese version isn't very good; we still need qwen.

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

The LIMI-Air-qx86-hi-mlx model is 97GB in size and works very well when deployed locally on a Mac with 128GB of RAM.

"model happier and more eager to explore and innovate"

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!

Could you please upload a 99GB-100GB version of the MLX quantization model so that it can be deployed locally on a 128GB RAM MAC? Thank you very much!