Austin Vance

austinbv's activity

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

New activity in mlx-community/deepseek-ai-DeepSeek-V4-Flash-4bit 3 months ago

Is it possible to convert to a 2-bit quantized version?

1

#1 opened 3 months ago by

hehua2008

New activity in mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX over 1 year ago

Conversion request to Q5_K_M for MLX

6

#4 opened over 1 year ago by

websprockets

New activity in mlx-community/meta-llama-Llama-4-Scout-17B-16E-4bit over 1 year ago

ValueError: Model type llama4 not supported.

4

#1 opened over 1 year ago by

jtdavies

New activity in mlx-community/CodeLlama-70b-Instruct-hf-4bit-MLX over 1 year ago

Conversion request to Q5_K_M for MLX

6

#4 opened over 1 year ago by

websprockets

Conversion request to Q5_K_M for MLX

6

#4 opened over 1 year ago by

websprockets