Unverified50% confidenceFactExact time
Serverless LoRA fine-tuning of Qwen 3.5 2B was performed on the Crusoe Intelligence Foundry platform, and this training cost only about 45 cents.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/18/2026
First Seen
Valid until: 12/2/2026
Sources
Small Model Fine-Tuning Upset: 2B/4B Parameters Beat GPT-6 Luna
youtubeNeuralNine11/18/2026
Related Entities
Related Claims
UnverifiedR1的基座模型V3训练成本仅558万美元,后续强化学习部分花费29万美元68% similarUnverified基于开源模型使用LoRA、QLoRA等微调方法的成本可低至数万美元,远低于从零训练所需的上亿美元67% similarVerifiedXiaomi officially disclosed that the total training cost of MiMo-V2.6 was only $3.5 million.66% similarUnverifiedAcross five hands-on coding tasks by a YouTube creator, Qwen 4 Max's total cost was about 1.65 + 0.64 + 1.26 + 0.29 USD (the cost of the fifth task was not explicitly listed), with per-task cost far below the compared Claude models.65% similarUnverifiedThe experiments use three mid-tier judges: two local models (Qwen 9B/4B, run via Ollama) and one gpt-4o-mini, with total API spending of $0.29.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1185318API
curl https://kongchang.com/api/v1/knowledge/claims/1185318MCP
get_claim(id=1185318)