Skip to content
8BitsForgeContact

Lab Notes7 field reports

All Lab Notes

Tag archive

#qwen3-8

Qwen3.8 · 4 field reports

Filed under Local AI (4). All tags.

Chronological feed

  1. Local AI · 10 min read

    Same Weights, Different Engine: XeStrata on the Arc Pro B70, and the Conversation That Survived a Restart

    A second engine for the same Qwen3.8 model wins on speed, then learns to keep long conversations on the SSD. Also: the test harness that asked us to load the wrong model.

    Approved for the main role. Same weights, tuned XeStrata: decode +6 to +15%, prompt reading +40 to +62%, quality 12/12 like production. Our fork resumes long conversations from SSD after a restart. Its SSD write volume needed one more fix, now being measured.

  2. Local AI · 10 min read

    Squeezing Qwen3.8 Until It Cried: A 46.9% Speedup and One Optimization Too Far

    A 46.9% Qwen3.8 speedup, a production qualification, and the tempting 64K shortcut that failed when the benchmark got serious.

    Promote the full-vocabulary checkpoint: 46.88% faster decode, qualified behavior, and no support for the later 64K shortcut.

  3. Local AI · 10 min read

    210K Context on a 32 GB Arc Pro B70

    Three identical cold starts, 179,525 prompt tokens, and a rollback regex that briefly became the main character.

    Admitted — the production route passed exact near-180K recall and the complete recovery, vision, reasoning, tool, and MTP suite.

  4. Local AI · 9 min read

    Qwen3.8 Flash-Next on One Arc Pro B70

    Fifteen tokens per second, one extremely narrow memory edge, and several acceleration ideas asked to leave the laboratory.

    Promising isolated batch-worker profile, not a production route.