Unverified50% confidenceReleaseExact time
The model codenamed iQuest Q1 has been open-sourced; it adopts an MoE architecture with a total of 320B parameters, 15B activated per token, and a context length of 512K.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/30/2026
First Seen
Valid until: 12/29/2026
Sources
Related Entities
Related Claims
Unverified目前主流编程模型的上下文窗口从32K到1M Token不等，Qwen系列部分模型支持到1M70% similarUnverifiedFor a 32-layer, 4096-dimensional model, the KV Cache for processing 2048 tokens occupies approximately 1 GB of VRAM70% similarUnverifiedThe model has 550 billion parameters, activates 55 billion parameters, uses a 550B-A55B architecture, and is an open-source model.70% similarVerifiedQLoRA quantizes the base model weights in 4-bit NF4 format, making it possible to fine-tune a 13-billion-parameter model on a single GPU.69% similarUnverifiedColibri covers 9 model families with parameters ranging from 744B to 2.8T, claiming that frontier models can run starting from 16GB of memory.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/962547API
curl https://kongchang.com/api/v1/knowledge/claims/962547MCP
get_claim(id=962547)