Unverified50% confidenceEventExact time
Phase 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".
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPhase 1 used an RTX PRO 4000 24GB to run Qwen2.5-1.5B-Instruct deployed via vLLM, with one reply shown in Open WebUI.72% similarUnverifiedShanghai Artificial Intelligence Laboratory released the Intern-S2 Preview 397B open-source model, making all weights available under the Apache 2.0 license.67% similarUnverifiedAfter ODS installation is complete, the dashboard opens at localhost:3001 and loads Qwen series lightweight models by default.63% similarUnverifiedQwen3.8-27B is now available for access through the Nebius platform.63% 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.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1052608API
curl https://kongchang.com/api/v1/knowledge/claims/1052608MCP
get_claim(id=1052608)