ModelScope(@ModelScope2022):Only ~1.2B parameters active at a time. Edge0-8B-A1B-preview makes an 8B-class MoE practical for local inference.📜 Apache 2.0. 🤖 https://t.co/xJ8uHG80kB ⚡ Reaches 23.9–25.3 tokens/s with about 1.0 GiB peak active memory in the reported short-context benchmark. 🏆 Retains most of the FP16 base model’s quality, with an average gap of just 2.8 points across five benchmarks. MMLU-Pro rises from 65.8 to 70.1. 🧠 SSD expert offload keeps most weights outside active memory, while a prerouter predicts which experts each layer will need next. 🛠 Recover-LoRA offsets quality loss from 4-bit quantization and expert offloading. The current Preview runs locally through MLX on Apple Silicon.

ModelScope@ModelScope2022

2026.09.15 11:30

Only ~1.2B parameters active at a time. Edge0-8B-A1B-preview makes an 8B-class MoE practical for local inference.📜 Apache 2.0. 🤖 ⚡ Reaches 23.9–25.3 tokens/s with about 1.0 GiB peak active memory in the reported short-context benchmark. 🏆 Retains most of the FP16 base model’s quality, with an average gap of just 2.8 points across five benchmarks. MMLU-Pro rises from 65.8 to 70.1. 🧠 SSD expert offload keeps most weights outside active memory, while a prerouter predicts which experts each layer will need next. 🛠 Recover-LoRA offsets quality loss from 4-bit quantization and expert offloading. The current Preview runs locally through MLX on Apple Silicon.

显示更多