AI article
Same config.json, different serve command: what to check before serving AREX-2
Community description: AREX-2 shares Qwen3.8-27B's architecture. The flags you reuse from the base model are where it breaks: drafter, MTP, FP8, context.
Dev.to | Oct 15, 2026 | InferenceKey
Automated excerpt
Every speed below is from the base model. Today you pick from BAAI's BF16 original (54. 7 GB), prithivMLmods' FP8 (35. 9 GB), cyankiwi's AWQ INT4 (20. 2 GB) or numsu's INT4 W4A16 (18. 6 GB). The drafter was trained against another model.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.