Cerebras Code now supports GLM 4.6 at 1000 tokens/sec (cerebras.ai) | HN Screenshots

YHacker Newsscreenshots

Screenshot of cerebras.ai: Cerebras Code now supports GLM 4.6 at 1000 tokens/sec

First screen, captured 11 months ago.

Looks similar

Screenshot of cerebras.ai: GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras

GPT-OSS 120B Runs at 3000 tokens/sec on Cerebras (cerebras.ai)

20 points by samspenc 11 months ago | 12 comments

Screenshot of cerebras.ai: Cerebras CS-4

Cerebras CS-4 (cerebras.ai)

441 points by sunils34 2 months ago | 256 comments

Cerebras product page introducing the CS-4, which the company bills as the fastest AI accelerator in the industry.

cerebras cs-4 ai-accelerator wafer-scale

Screenshot of claudiacode.com: Claudia – Desktop companion for Claude code

Claudia – Desktop companion for Claude code (claudiacode.com)

468 points by zerealshadowban 1 year ago | 214 comments

Landing page for Claudia, an open-source desktop GUI for Claude Code that manages sessions, custom agents, and usage tracking.

claude-code anthropic desktop-app gui

Screenshot of windsurf.com: Windsurf SWE-1: Our First Frontier Models

Windsurf SWE-1: Our First Frontier Models (windsurf.com)

140 points by arittr 1 year ago | 50 comments

Screenshot of about.gitea.com: Gitea Private, Fast, Reliable DevOps Platform

Gitea Private, Fast, Reliable DevOps Platform (about.gitea.com)

36 points by Bluestein 1 year ago | 39 comments

Screenshot of httl.dev: Show HN: A Fast HTTP Request CLI Powered by HTTL

Show HN: A Fast HTTP Request CLI Powered by HTTL (httl.dev)

39 points by emykhailenko 1 year ago | 11 comments