Qwen3.6-27B — Akka, MLX 6-bit (AR-only)

Why this artifact is unusual

1. A proved negative, not an absent one. The source carries a 15-tensor MTP draft head. We attempted full MTP contract calibration and it failed at 0.0% draft-target agreement — so we shipped without the head and we shipped the evidence of why. Most merge quants either silently strip the head or ship a broken one that loads fine and has no working draft acceleration. Here the failure condition is measured, documented, and reproducible: receipts/build_outcome.json (verdict contract_calibration_failed), receipts/calibrate.json (per-depth agreement arrays).
2. First MLX port of the Akka merge — the Tess/cultural-artifact lineage made runnable on Apple Silicon with a full, honest audit trail. This is the same pipeline that produced the Fable-711 MTPLX quants, so the two generations of nightmedia/DavidAU-adjacent art are directly comparable.
3. Comparative quality anchor, not a vibe. WikiText-2 PPL is reported as a pair against the Fable-711 MLX 6-bit artifact measured in the same harness, same machine, same window budget — so the +0.139 delta means something rather than an absolute number floating alone.
4. Reproducible to the failure. The MTP head here was added post-merge via script (per its author's own notes) and was never trained on this body. The receipts record the exact agreement numbers, so the diagnosis — and the training path that would fix it — is defined, not guessed.

Scope — read before assuming anything

• AR-only. No MTP. No speculative acceleration. MTP contract calibration against this merged trunk failed at 0.0% top-1 draft agreement (0/64 at every tested depth; even top-8 only 2/64; best_agreement = 0.0). Shipping that head would produce a model that "loads and generates fine" with a silently non-functional draft head — the worst failure mode, because nothing errors. It is therefore not included. Do not expect MTP or MTP-style speedups.
• No vision. The source is image-text-to-text (333 vision tensors). This conversion is the language body only; vision_config is absent.
• Not a quality claim. This is an early derivative intended as a health checkpoint and study artifact; a fresh blind behavioral eval is not yet complete (refusal/scoring harness runs planned).

What is included

• 20 GB, 5 safetensors shards, 6-bit affine, group 64.
• The language body is complete: all 848 source body-layer tensors are present; 0 dropped (1847 tensors total in the artifact index, including affine scale/bias companions).
• Verified on-device before upload: full index/shards resolve 1847/1847, AR generation coherent on the M5 Max.

Usage

Measured — M5 Max (128 GB), macOS 27.0, mlx 0.32.0, mtplx 2.6.0

Receipts (in-repo, receipts/)

Reproducibility

• Source pinned: nightmedia/Qwen3.6-27B-Akka (bf16, 12 shards).
• Forge recipe: body_bits=6, body_group_size=64, body_mode=affine, body_dtype=bf16, MTP contract calibration enabled and allowed to fail (it did). Same forge pipeline as the Fable-711 MTPLX 4/6/8-bit quants.
• Sequence: mtplx forge build --repo …/Akka-src --recipe <6bit> --branded-name Qwen3.6-27B-Akka-MTPLX-6bit → contract_calibration_failed → AR-only package published here.

Credits

• nightmedia — the Akka merge and its source card (nightmedia/Qwen3.6-27B-Akka). Tess lineage anchor: migtissera/Tess-4-27B.
• Qwen — Qwen3.6-27B base. MTPLX — forge/quant/Serve runtime.
• Package and audit by philipjohnbasile; see the linked discussion on the source thread for the calibration methodology.

Intended use / limits

• Research, study, and creative work — not a product claim.
• No MTP speedup; treat AR-only throughput (~20 tok/s on M5 Max class) as the ceiling for this artifact.
• If you need a working MTP build of this lineage, the head requires fine-tuning onto the merged body first — the calibration failure is the definition of that requirement, and it is now on record.