opentq-qwen36-bf16-sidecar

# Qwen3.6-27B BF16 Sidecar Runs This dataset publishes BF16 sidecar outputs used to compare OpenTQ GGUF artifacts against the base model `Qwen/Qwen3.6-27B` on pinned practical mini-subsets. The Dataset Viewer uses flattened Parquet tables so columns have stable types. The original raw JSON files remain in `runs/<job_id>/` for reproducibility. ## Tables | Config | Grain | Purpose | | --- | --- | --- | | `results` | one row per benchmark sample | prompts, task IDs, deterministic BF16 outputs, score fields, timing | | `benchmarks` | one row per benchmark per run | summary pass counts and pass rates | | `runs` | one row per sidecar job/mode | model, runtime, prompt format and aggregate metadata | ## Scope These are small release-quality signals, not full benchmark replacements. Use them for paired BF16-vs-GGUF regression checks only. Official full-harness Qwen scores remain the baseline for model capability claims. ## Related - Model repo: [`zlaabsi/Qwen3.6-27B-OTQ-GGUF`](https://huggingface.co/zlaabsi/Qwen3.6-27B-OTQ-GGUF) - Paired benchmark reproducibility dataset: [`zlaabsi/Qwen3.6-27B-OTQ-GGUF-benchmarks`](https://huggingface.co/datasets/zlaabsi/Qwen3.6-27B-OTQ-GGUF-benchmarks)