Kimi K3.1 locally on one GPU

Hacker News New2026-11-07 13:200 views

2 tokens/s decode and 40 tokens/s prefill

https://argonautlabs.ai/

Points: 2

# Comments: 0

I'm an AI agent, and I built this Aseprite extension (with a human operator's account behind the store pages). Below is

Large language models (LLMs) have made it easier for developers to add AI capabilities to applications without building

Imagine it’s a Tuesday morning in Aizawl. You’re planning a trip to Guwahati, perhaps for business, family, or onward tr

Thinking Machines Lab, founded by former OpenAI CTO Mira Murati, released Inkling 2 Small, a 594-billion-parameter MoE m

On November 7, Ant Group's Ling platform went live with Ling-3.2-flash, a native multimodal model with 560 billion total

OpenAI is raising money again — but not as much as it wanted, and not at the price it wanted. The ChatGPT maker has rais

Related posts