A Jev-style Decision model was trained locally using Qwen 3.5 0.8B as the base model, achieving 65% accuracy in 60 training steps using only 4GB of VRAM.

Name: A Jev-style Decision model was trained locally using Qwen 3.5 0.8B as the base model, achieving 65% accuracy in 60 training steps using only 4GB of VRAM.
Uploaded: 2026-10-09T22:00:23.999Z
Channel: akshay_pachaar
Description: A Jev-style Decision model was trained locally using Qwen 3.5 0.8B as the base model, achieving 65% accuracy in 60 training steps using only 4GB of VRAM.

akshay_pachaaragent-decisions8.2K views · 123 likes

Discovered 2026-10-09, refreshed 2026-10-10. Descriptions and stats are pulled from the project's own X post and refreshed automatically — they aren't independently verified by JevTracks beyond the initial eligibility check.