@ModelScope2022: Nanbeige4.2 @nanbeige lands on ModelScope with two models: - 28T-token Looped Transformer base - 3B SFT+RL agent for to…
Summary
Nanbeige4.2 has been released on ModelScope with two models: a 28T-token Looped Transformer base and a 3B SFT+RL agent that reportedly outperforms Qwen3.5-9B and Gemma4-12B on agent benchmarks.
View Cached Full Text
Cached at: 07/22/26, 10:37 PM
🚀 Nanbeige4.2 @nanbeige lands on ModelScope with two models:
- 28T-token Looped Transformer base
- 3B SFT+RL agent for tools, coding, reasoning, office work & deep research
📊 Team-reported wins over Qwen3.5-9B and Gemma4-12B on agent benchmarks. 🤖 https://t.co/O80cFFbG80 https://t.co/YnhPK5R3L4
Similar Articles
Nanbeige/Nanbeige4.2-3B
Nanbeige4.2-3B is a compact agentic model using Looped Transformer architecture, demonstrating strong performance on agentic and reasoning benchmarks at the 3B scale, outperforming larger models such as Qwen3.5-9B and Gemma4-12B.
New Model: Nanbeige4.2-3B (Looped Transformer, outperforms 4x size)
Nanbeige4.2-3B is a new 3B parameter AI model using a looped transformer architecture that outperforms models 4x its size.
@xdotli: ICYMI Nanbeige 4.1, a 3b model released by Chinese Indeed, outperforms Qwen3-30b-A3b + Qwen 3.5 4b. It can finish long …
Nanbeige 4.1, a 3B model from Chinese Indeed, outperforms larger Qwen models on tasks requiring 600+ tool calls.
@ModelScope2022: Qwen-AgentWorld just dropped two releases on ModelScope! An open 35B total / 3B active MoE world model with 256K contex…
Qwen-AgentWorld releases an open 35B total / 3B active MoE world model with 256K context, along with a 7-domain benchmark, achieving state-of-the-art performance on AgentWorldBench.
Agentic AI at Two Different Scales: Nanbeige4.2-3B and Laguna S2.1 (9 minute read)
Compares two new AI models for agentic workloads: the compact Nanbeige4.2-3B with a looped transformer architecture and the large Mixture-of-Experts Laguna S2.1, both released on Hugging Face.