Patrick Devine (@pdev110) profile picture

Software Guy @ Ollama

San Francisco Bay Area
Joined May 2014
Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)Photo by Patrick Devine (@pdev110)
For your pandemic Friday viewing enjoyment. 'kubectl run -it --rm --image=ghcr.io/pdevine/thisisfine tif' or for the docker inclined 'docker run -it --rm ghcr.io/pdevine/thisisfine'
2
1
1
9
Replying to @brockpierson
Only Windows 3.11. And we used IPX to have 4 player Doom LAN parties.
1
2
63
More @thinkymachines inkling-2-mini running in @ollama w/ @NousResearch Hermes CLI. I just love that it was able to take screenshots of its progress and show it in the harness.
1
7
431
Playing around with inkling-2-mini on @ollama v0.40.17-rc3. It's pretty dope so far and runs well on a 32GB Mac. This is my standard "make an html5/js asteroids game so colourful that it makes my eyes bleed" prompt.
1
2
14
3,289
What kind of machine are you rockin'?
10
Replying to @martin_casado
Look Martin, no computer!
1
58
Replying to @iamkennethchan
My $0.02 is that we should build a high speed line between Pacific Central to Abbotsford to connect with YXX, and then to the border. There is already a rail alignment there, and Seattle is a lot further East than Vancouver anyway.
2
2
187
Replying to @AlexKolicich
Mostly sane results on the ballot props. I wish we could build more housing so we didn't have to sell bonds to give loans to people to be able to afford a house.
1
1
138
Replying to @martin_casado @bot
Orac from Blake's 7 is the only answer.
1
1
106
Yep. Speech output is only on the mac, but input is for mac+pc.
21
Replying to @rexsalisbury
Keep the train yard but put a lid over it and then put homes/stores over the top of that and use the proceeds to pay for the tunnel to the transbay terminal, amiright?
1
256
Patrick Devine retweeted
.@GoogleDeepMind EmbeddingGemma 2 is now available on Ollama. Made for consumer devices and is multimodal. ollama pull embeddinggemma-2
Meet EmbeddingGemma 2, our first natively multimodal open model for on-device embeddings. It expands beyond text to unify code, images, audio, and video in a shared space. 🧵
25
49
5
669
35,623
Replying to @ronaldmannak
Ich brauche die vegane Version davon in meinem Leben.
1
22
We defaulted to the 8bit models, so Nimble is about 9.5GB and Tev1 is between 4.5GB and 800MB. There is a 4bit quantization for Nimble that is about half the size though, but it loses some quality.
1
14
Patrick Devine retweeted
Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playing Ollama racer through the new local /v1/systemone API by making decisions in real-time. 🏎️
175
605
122
4,586
669,205
Replying to @mustafajamil
My wife told me about someone the other day going off on oxford commas. It's just wild out there.
12
Replying to @martin_casado
I mean, someone's gotta hack the Gibson, right?
1
119
Replying to @farquaadguy @ddalcu
Yes, I saw the post, but I also ran some benchmarks on Qwen3.8. It's much closer than what this graph shows, even at each of those prompt sizes.
11
Replying to @farquaadguy @ddalcu
It's very fast, but it's not comfortably 2x faster. The posted benchmarks for Ollama used the llama.cpp backend and not the MLX backend, and it had spec-decoding turned off. In reality I think it's closer to around 10% on prefill and a bit faster than that on decode.
1
34