Tagged qwen
2 entries
2026-10-05
Brief · 5 October 2026Qwen 3.8 Flash Next (125 B) was benchmarked on a consumer RTX 4090 and hit a peak of 100 T/s token throughput, a record for a model of this size on desktop hardware.
2026-07-19
Brief · 19 July 2026A leak of Qwen 4.0 appeared on YouTube, and DeepSeek announced its V4 model will go GA on Monday, adding two new LLM contenders in the last 36 hours.