---
license: cc-by-4.0
tags:
- quantization
- ternary
- mlx
- gated-deltanet
- qwen3.5
---

# Where Can Qwen3.5 Decision Models Afford Low Precision? A Sub-3-Bit Sensitivity Map, Runtime-Priced Byte Accounting, and an Equal-Size Check of Hand Recipes (working draft)

**Working draft v9.1 (2026-10-07), working paper, not peer reviewed.** Numbers may still change as remaining runs finish.

📄 [kev-d3-paper-draft-v9.1.pdf](./kev-d3-paper-draft-v9.1.pdf) (current)

Per-module sub-3-bit sensitivity of two Qwen3.5 hybrid decision models (Gated DeltaNet linear attention interleaved 3:1 with full attention), measured as option-distribution KL under binary / ternary / 3-bit / 4-bit GPTQ, with a measured-KL allocation (a multiple-choice knapsack priced in the target runtime's storage format; called HyBitQ in earlier drafts) that turns the measurements into bit allocations.

Related release: [Jakevin/kev-4b-ternary-mlx](https://huggingface.co/Jakevin/kev-4b-ternary-mlx) (revision `v2.0` uses this allocation; `v1.0` is the earlier hand-designed recipe).

| Kev-4B | decision-v7 retention | held-out retention | size |
|---|---|---|---|
| v1.0 (hand recipe + rank-16 adapter) | 96.8% | 86.5% | 1.679 GB |
| v2.0 (measured allocation, no adapter) | 99.2% | 94.5% | 1.678 GB |

## Earlier versions

- [kev-d3-paper-draft-v8.pdf](./kev-d3-paper-draft-v8.pdf): superseded draft v8 (2026-10-07).
- [kev-d3-paper-draft-v6.pdf](./kev-d3-paper-draft-v6.pdf): superseded draft v6 (2026-10-07).
- [kev-d3-paper-draft-v2.pdf](./kev-d3-paper-draft-v2.pdf): superseded draft v2 (2026-10-07, earlier title "Where Can a Hybrid Linear-Attention Model Afford One Bit?", still contained [TBD] sections). Kept so existing links keep working.