Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sroussey
1 day ago
|
parent
|
context
|
favorite
| on:
Benchmarking Qwen3.8 27B quantizations: 4-bit hold...
Have you tried
https://huggingface.co/prism-ml/Bonsai-27B-mlx-1bit
? PrismML is the only people i am aware of doing 1bit that is decent.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
