6 3 1

Alexander Gusev

alexgusevski

AI & ML interests

Open Source, running stuff on my M4. Check out anemll-server: https://github.com/alexgusevski/anemll-server

Recent Activity

reacted to ritvik77's post with ❤️ 6 days ago

Big companies are now training huge AI models with tons of data and billions of parameters, and the future seems to be about quantization—making those models smaller by turning big numbers into simpler ones, like going from 32-bit to 8-bit without reducing accuracy by +/- 0.01%. There should be some standard unit of measurement for the ratio of model size reduction to accuracy lost. What do you all thing about this ?

new activity 7 days ago

mlx-community/mlx-my-repo:Update to latest mlx_lm version?

updated a collection 8 days ago

MLX Models

View all activity

Organizations

None yet

Collections 2

models 179

datasets

None public yet

Alexander Gusev

AI & ML interests

Recent Activity

Organizations

Collections 2

alexgusevski/Reverb-7b-mlx

alexgusevski/Reverb-7b-q8-mlx

alexgusevski/Reverb-7b-q6-mlx

alexgusevski/Reverb-7b-q4-mlx

alexgusevski/anemll-Llama-3.2-1B-Instruct-ctx512_0.1.2

alexgusevski/anemll-Llama-3.2-1B-Instruct-ctx1024_0.1.2

alexgusevski/anemll-Llama-3.2-1B-Instruct-ctx1546_0.1.2

alexgusevski/anemll-Llama-3.2-1B-Instruct-ctx2048_0.1.1

models 179

alexgusevski/gemma-3-text-4b-it-q6-mlx

alexgusevski/gemma-3-text-4b-it-fp16-mlx

alexgusevski/gemma-3-text-4b-it-q8-mlx

alexgusevski/gemma-3-text-4b-it-q4-mlx

alexgusevski/gemma-3-text-4b-it-q3-mlx

alexgusevski/EXAONE-Deep-32B-mlx-fp16

alexgusevski/EXAONE-Deep-32B-mlx-8Bit

alexgusevski/EXAONE-Deep-32B-mlx-6Bit

alexgusevski/EXAONE-Deep-32B-mlx-4Bit

alexgusevski/EXAONE-Deep-32B-mlx-3Bit

datasets

Alexander Gusev

AI & ML interests

Recent Activity

Organizations

Collections 2

models 179 Sort: Recently updated

datasets

models 179