
Building AI Inference & Coding tools Working on š§ @penginlabs.
New York, USA
Joined January 2010
- Tweets3.1K
- Following509
- Followers314
- Likes6.2K
I really want to hear your comments and advices on this project:
nitter.gq/erdemwrites/status/212ā¦
When I listened to what Sam Altman said and don't want to kill potential of Ram sitting in my unused computers anymore and kiln is born. I really want to hear your comments and advices..
github.com/erdemozkan/kiln
1
79
This is a huge step for the local AI ecosystem. Iāve seen people complain about their computersā fans getting noisy when they run these models. I guess they havenāt been near a data centerāyou can hear the rigs from half a mile away on a quiet day š
nitter.gq/SamuelZengML/status/21ā¦
Introducing Edge0-145B and Edge0-120B, @Edge0_AIās first device-native 100B-class foundation models with open weights.
Cloud-level intelligence on your laptop. Free, offline, and fast enough for real vibe coding.
- Smart: beats Claude Opus 4.6 on Terminal-Bench 2.1 (86.5% vs. 78.2%)
- Light: needs just 29G memory, 1/3 of a standard setup (100G+)
- Fast: decodes 75+ toks/s, prefills 1050+ toks/s on RTX Spark and Mac.
- Steady: handles 128Kā256K tokens of context without slowing down, even on long tasks
Frontier-class agentic coding. No cloud API. No token bill. Your code and data never leave your machine.
Open weights are live on @huggingface. Run it locally or plug it into your favorite coding agent.
2
47
When I listened to what Sam Altman said and don't want to kill potential of Ram sitting in my unused computers anymore and kiln is born. I really want to hear your comments and advices..
github.com/erdemozkan/kiln
It's the first time Claude has said this to me. Is it an Opus 5.5 thing or just a random moment? BTW, something happened to Codex and my usage credits expire unusually quickly..
3
80
Weāre collecting device compatibility data for a WebGPU alternative weāre developing.
The test takes 20 seconds max; no signup, no product testing.
claude.ai/code/artifact/fc7cā¦
Especially interested in seeing results across different browsers, GPUs, and OS..
@qazwsx23310 @jun_song @andrewchen
3
59
This was a personal computer MVP from the late 1970s.
A good reminder that first versions donāt need to be perfect. They just need to solve a real problem.
Sometimes weāre overengineering software that should have been shipped months ago..
2
3
74
I was 6 years old when I first learned typing on an Amstradš
Today, weāre talking about 1T param AI models.
Our generation is unique;we experienced both the primitive days of PC era and the rise of advanced AI within a single lifetime.
What computer did you learn to type on?
17M tokens/day locally is really promising..
nitter.gq/0xSero/status/20584644ā¦
1
3
118
Business owners are actually very happy with local AI solutions.
They donāt want to send their data to external servers and recurring AI API costs.
They just want AI running on their own computers for a specific task..
One of them told me:
āAll I need is AutoCAD, not DaVinci.ā
2
5
128
This is called history..
nitter.gq/sequoia/status/2039434ā¦
In honor of 50 years of Apple, we're sharing - for the first time ever - Don Valentine's original 1977 memo for Sequoia's investment into Apple Computer. #Apple50
6
121
It's this easy to try using yolo-coder to start fixing your code errors. I need to hear your comments..
6
90













