Unverified50% confidenceEventExact time
The 77GB coordinator model gpt-oss:120b cannot share the same machine with the worker models it calls, and each task delegation triggers about 100GB of model swapping, with a simple greeting taking nearly five minutes.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/14/2026
First Seen
Valid until: 1/12/2027
Sources
Related Entities
Related Claims
Unverified70B参数模型权重从网络存储传输到GPU显存需要数分钟时间74% similarUnverifiedAfter downgrading the coordinator to gpt-oss:20b (about 14GB), about 60GB of memory is left free, enough to perform coordination and image generation simultaneously, with no swapping and no daemon rejections.73% similarUnverifiedAfter migrating the worker models to a second host with a 5600G equipped with a GTX 1060, gpt-oss:120b stayed resident throughout a long run of 1 hour and 46 minutes with no swapping at all, and orchestration reliability surpassed Gemma.72% similarUnverifiedThe TEMPEST model has only 720,000 parameters, a storage footprint of 2.80 MB, and is able to converge within 50 training epochs.71% similarUnverifiedThe Workers runtime lacks file system access, limits CPU execution time per request to a maximum of 50 ms, caps memory at 128 MB, and the free tier provides 100,000 requests per day.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1025785API
curl https://kongchang.com/api/v1/knowledge/claims/1025785MCP
get_claim(id=1025785)