Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ksubedi
15 hours ago
|
parent
|
context
|
favorite
| on:
Mistral Medium 3.5
Let's not forget Qwen 35B A3B MoE. It gets better performance than this in all the metrics for a fraction of the memory / compute footprint.
Sad to see all the non Chinese open source models being at least one generation behind.
help
simjnd
15 hours ago
[–]
Qwen3.6 27B is even more impressive IMO. Dense so it doesn't run as fast but it's so good.
reply
trueno
9 hours ago
|
parent
[–]
im kinda torn on which to download. i have the headroom to run either, mostly just want the occasional "do a coding thing im too lazy to do"
reply
Consider applying for YC's Summer 2026 batch! Applications are open till May 4
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Sad to see all the non Chinese open source models being at least one generation behind.