Founder, The AI Conformity Institute. Helping organisations understand and comply with Global AI Regulations.
Waterford, Ireland
Based in Spain
- Tweets 3,720
- Following 418
- Followers 557
- Likes 15,383
Maybe Ornith 35b, I have had some decent speeds in the past with the moe models. Although I would love a smaller moe from qwen 4.
1
42
I tried this dudes setup yesterday and its really quite good on my 3060.
Bonsai 2 27b from @PrismML can do Computer Use ✅
Here is Bonsai 2 27b, on my own 12gb GPU, planning a trip to the Art Institute in Chicago for me.
93.5 tok/s, 56s, 6 steps with reasoning.
More details / videos : bonsai.puppetmaster.gg/
2
6
233
William Devine retweeted
Bonsai 2 27b from @PrismML can do Computer Use ✅
Here is Bonsai 2 27b, on my own 12gb GPU, planning a trip to the Art Institute in Chicago for me.
93.5 tok/s, 56s, 6 steps with reasoning.
More details / videos : bonsai.puppetmaster.gg/
4
6
60
6,691
Using Frontier AI model for most of what you are using them for is like using an F1 car to do a school run.
As in.. its awesome.
1
2
61
