qazplm17
Joined 5 years ago
Karma
4
Submissions
5
Member since
Sep 25
Recent submissions
Comment · 6 months ago
It won’t be a fair comparison against opus-4.6 but it will run quite well on your machine. I’ve tested qwen3.5 27B, Gemma4, minimax2.5 and Glm4.7 before on my m3 ultra. And i’d say this is the first model that I’m able to use for full agentic sessions. here is a pi session i just did and it worked quite well surprisingly: https://pi.dev/session/#c3d003becb1bfcc7ffbca04e89e1adf8
Comment · 6 months ago
Just tried to use qwen3.6-35b-a3b-bf16 + omlx running a pi session to use my HN cli to do a sentiment analysis on this story and opus4.7 story. I’m getting ~40tk/s on a M3 Ultra Mac Studio and the tool use consistency has been held up well. Even when passing 100k tokens, the session was still going strong. Here is the full sentiment analysis report it produced:
https://gist.github.com/duh17/2db5351da026cec4bd4f46e169e75e...
Here is the full session:
https://pi.dev/session/#c3d003becb1bfcc7ffbca04e89e1adf8
This is by far my smoothest agentic session using a local model of any size. The output quality and speed has really struct the right balance. Very impressive release
Comment · 8 months ago
Pi treats you like an adult and shows whatever the fuck LLM is doing rather than actively hiding shit from the user. And just for that, once you tasted the freedom and transparency, there’s no way to go back to CC.
Comment · 9 months ago
I have similar setup, one thing to add is map action button to a shortcut for dictate to clipboard since you can’t dictate directly into termius.
Comment · 1 year ago
Not sure why you are giving plugs for two lesser-known VPN providers (at least I’ve never heard of them) that are adopting less secure practices such as requiring email for sign-up and are more expensive than Mullvad, that is widely considered one of the most trusted VPN providers. Also I’m currently using Mullvad in mainland China right at this moment, it works perfectly fine.