Independent eval puts Prism-LM's Bonsai 2 QAT models at ~91% accuracy

airesearch12 · x · 2026-09-19

ByteShape independently benchmarked Prism-LM's new Bonsai 2 QAT (quantization-aware training) models on the Qwen3.8 series, reporting roughly 91% — a solid result.

The numbers come from ByteShape's own runs using Prism's runtime, not Prism's reported benchmarks, with the rest of the setup consistent with their earlier Qwen3.8 evaluations.

Related event: Bonsai 2 QAT quantized model scores ~91.5% in independent benchmarks(2 posts)→

Original post →

More from Models

Models channel →