Unverified50% confidenceEventExact time
Phase 1 used an RTX PRO 4000 24GB to run Qwen2.5-1.5B-Instruct deployed via vLLM, with one reply shown in Open WebUI.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPhase 2 used an A100 SXM 80GB to run Qwen3.8-27B BF16, serving an OpenAI-compatible interface via vLLM, and the model replied in Japanese as instructed with "接続確認できました".72% similarUnverifiedThe WEXTL platform claims to support 1,200+ integrations.62% similarUnverifiedInstalling this version requires a supported Node environment (22.1, above 19, or level 24 and above), and after installing via the official NPM package, the web interface is launched to configure the provider and API key.61% similarUnverifiedThe Qwen 2.5 series offers multiple parameter sizes ranging from 0.5B to 72B and adopts the Apache 2.0 open-source license, which permits commercial use.61% similarUnverifiedThe API for Qwen2.5-Max-0902 is now live, and products such as Qianfan Office, Coder, and Qianfan App have completed integration.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1052604API
curl https://kongchang.com/api/v1/knowledge/claims/1052604MCP
get_claim(id=1052604)