Liquid AI open-sources on-device benchmark Pipette
It measures speed and memory by model-quantization-runtime-device combination, and ships with over 10,000 verified results
30
Tag
quantization
Qwen3.8-27B released as open weights under Apache 2.0
Alibaba's Qwen has opened up the full weights of its 27B multimodal model. At 4-bit precision it's 17.9GB — small enough to fit on a single graphics card — yet the official chart shows it beating Claude Opus 4.6 Max on several metrics.
150
That's the last story.