This is chat jimmy, a demonstration from the company called Taalas, the company from Finland 🇫🇮 AMD recently purchased.
It demonstrates the speed of a llama 7b on their chip, 14k t/s. I remember seeing an article that they froze a qwen 3.5 27b in to the silicon, promising
Qwen 3.8 vs Gpt 5.6 Sol vs Fable 5 vs Fable 5.1
Artificial intelligence platform Perplexity has unveiled a new Hybrid mode for its Mac version.
This mode works with an optimized language model called PPLX Qwen 3.8 27B. Its interesting feature is a security layer called Privacy Gate, which detects sensitive and personal data before sending your information to the cloud.
GLM 5.3, GPT 5.6 Luna, Claude Opus 5, Grok 4.6, DeepSeek V4, Kimi K3, and a cloud browser for agents - all FREE.
DuckDuckGo: GPT 5.6 Luna and older models, no signup: LM Arena: free side-by-side, Opus 5, GPT-5.6 Sol, Grok 4.6, Qwen 3.8 Max:
You have reached the end of the archive
All of qwen38