“어떤 LLM이 내 컴퓨터에 맞을까?”
그런 고민을 하는 당신!
여기 개쩌는 도구가 있으니 바로 ‘llmfit'
하드웨어 스팩을 확인해주고 구동 가능한 최적의 LLM을 알려주는 매우매우 유용한 사이트!!
심지야 토큰 처리 예측까지 미리 확인할 수 있으니 로컬 개발자라면 못참겠지?
llmfit. Useful tool that probes hardware and tells you exactly which LLMs will actually run.
- handles MoE expert offloading, picks the best quantization for your RAM, estimates tokens/sec before you even pull the weights.
Essential for local dev.
https://t.co/qn8PmqQNbV
🚨BREAKING: You can now run Claude Code for FREE.
No API costs. No rate limits. 100% local on your machine.
Here's how to run Claude Code locally (100% free & fully private):
STATE OF THE PRODUCT JOB MARKET IN EARLY 2026
In spite of the headlines about layoffs and AI taking jobs, we’re actually seeing a lot of promising signs in tech hiring, and some interesting new trends:
1. PM openings are at the highest levels we’ve seen in over three years
2. AI hasn’t slowed the demand for software engineers (at least not yet)
3. AI roles in general are absolutely exploding
4. Design roles have plateaued
5. The Bay Area is increasing in importance
6. Remote work opportunities continue to decline
7. Despite ongoing layoffs, the overall number of tech jobs continues to grow
More in 🧵
-추가 확인 결과-
앤트로픽이 오픈클로에 대응해 클로드 코드채널 기능을 3월 20일에 별도로 출시함.
오픈클로 자체가 클로드 앱에 들어간 게 아님!
디코나 텔레그램을 통해 Claude Code를 텍스트로 제어하는 기능으로, 오픈클로의 인기에 대응하기 위한 앤트로픽의 자체 서비스임.
-결론-
맥미니 필요 없음 = 24시간 비서 혹은 LLM, API 자체연동 하실거 아니고 본 컴퓨터에서 쓰면서 잠깐잠깐 쓰는거면 없어도 됨
클로드가 오픈클로 기능 탑재 = 출처도 없고 확인도 안됨
비용 29000원 = 클로드 구독 비용임 한계가 도달하고 더 쓸거면 추가비용 내야됨
📢 Jack Black Announces 📢
"Yo, listen! If you’re out here ripping avatars on VRChat, you’re stealing someone’s soul, man. Knock it off, I'll join the VRChat team myself if I have to!"
Upgrading your RAM is now unnecessary.
Introducing our new ComfyUI Dynamic VRAM optimization. Running local models is now possible on even the most memory constrained hardware.
Read more here:
https://t.co/H1ZeYLlfzf
Yesterday we found out Qwen3.5-27B (dense) beats both the 35B and 122B MoE variants at UI replication from screenshots.
Today's question: what about Jackrong's Qwen3.5-27B-Claude-Opus-4.6-Reasoning-Distilled?
A distilled 27B with Claude Opus 4.6 reasoning baked in. So I put all 3 in the ring:
- Qwen3.5-27B
- Qwen3.5-27B-Claude-Opus-Distilled
- Claude Opus 4.6
Since the distilled model isn't multimodal, I gave all three the same detailed text prompts describing the UI components from yesterday's test.