Diskless Linux boot using ZFS, iSCSI and PXE
(news.ycombinator.com)
1.
2.
Usage-based pricing killing your vibe, here's how to roll your own local AI
(news.ycombinator.com)
3.
Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model
(news.ycombinator.com)
4.
Even 'uncensored' models can't say what they want
(news.ycombinator.com)
5.
We got 207 tok/s with Qwen3.5-27B on an RTX 3090
(news.ycombinator.com)
6.
Kimi K2.6: Advancing open-source coding
(news.ycombinator.com)
7.
Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving
(news.ycombinator.com)
8.
Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7
(news.ycombinator.com)
9.
Qwen3.6-35B-A3B: Agentic coding power, now open to all
(news.ycombinator.com)
10.
Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All
(news.ycombinator.com)
11.
12.
Qwen3.6-Plus: Towards real world agents
(news.ycombinator.com)
13.
Qwen3.6-Plus: Towards Real World Agents
(news.ycombinator.com)
14.
Running local models on Macs gets faster with Ollama's MLX support
(arstechnica.com)
15.
$500 GPU outperforms Claude Sonnet on coding benchmarks
(news.ycombinator.com)
16.
LLM Neuroanatomy II: Modern LLM Hacking and Hints of a Universal Language?
(news.ycombinator.com)
17.
Flash-MoE: Running a 397B Parameter Model on a Laptop
(news.ycombinator.com)
18.
MacBook M5 Pro and Qwen3.5 = Local AI Security System
(news.ycombinator.com)
19.
Qwen3.5-397B at 4.74 tok/s using 5.9GB RAM
(news.ycombinator.com)
20.
Qwen3.5 122B and 35B models offer Sonnet 4.5 performance on local computers
(news.ycombinator.com)
21.
Qwen3.5: Towards Native Multimodal Agents
(news.ycombinator.com)
22.
New coding models and integrations
(news.ycombinator.com)
23.
Qwen3-Omni: Native Omni AI model for text, image and video
(news.ycombinator.com)
24.
Evaluating LLMs for my personal use case
(news.ycombinator.com)
25.
26.
27.
28.
Qwen3-Coder: Agentic coding in the world
(news.ycombinator.com)
29.
Qwen3-Coder: Agentic Coding in the World
(news.ycombinator.com)