Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
syntaxing
9 days ago
|
parent
|
context
|
favorite
| on:
Benchmarking Qwen3.8 27B quantizations: 4-bit hold...
I’m more curious how each 4 bit quant compares. It seems like NVFP4 outperforms Q4_K_M in terms of speed and top 1 but is only good for expensive Nvidia cards
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: