alesha-pro/qwen38-flashnext-strata-4x3090
Qwen3.8-Flash-Next on 2x RTX 3090: 150 tok/s on code, 262K context. Strata 0.2.10 + unsloth UD-IQ4_XS + DFlash2. Full recipe, refusal vectors, session patch, raw benchmark traces.
GitHub repository with 10 stars and 1 forks.
Language: Python
Topics: abliteration, gguf, llm, local-llm, qwen, rtx-3090, speculative-decoding, strata