Tag
A developer shares progress on training a 7B parameter open source LLM from scratch using a DeepSeek architecture optimized for low VRAM, with the goal of democratizing AI development and eventually surpassing large proprietary models.
Author shares a working llama-server config to run the 35B-MoE Qwen3.6 model on an 8GB RTX 4060, highlighting a max_tokens trap caused by unconstrained internal reasoning and the fix using per-request thinking_budget_tokens.