---
library_name: mlx
license: apache-2.0
base_model: Qwen/Qwen3.6-35B-A3B
base_model_relation: quantized
tags:
- mlx
- oQe
- enhanced
- mixed-precision
- moe
- agentic
track_downloads: true
---

# Qwen3.6-35B-A3B — oQe Series

This repository contains **Enhanced (oQe)** MLX quants for the original **Qwen3.6-35B-A3B**. While standard quants are often made in one "streaming" pass, the **oQe** series uses a multi-stage optimization path to make sure the model doesn't lose its "intelligence" at lower bitrates.

### 🚀 The oQe (Enhanced) Build Path
We move away from simple rounding and use a more deliberate process to protect the model's logic:

1.  **Sensitivity Mapping:** We don't guess which layers are important. We run a calibration pass to measure exactly how much precision each layer needs to keep its output stable.
2.  **Hessian-Based Tuning:** Every time we round a weight to a lower bit, we adjust the surrounding weights to compensate for the error. This keeps the model's internal math from "drifting" as it gets smaller.
3.  **Unified Batching:** For this MoE architecture, we process all 256 experts together so the 8+1 routing path stays stable and precise.

### 📋 oQ Build Performance Matrix

| Tier | Target bpw | Actual bpw | Size | Precision Boosts | Hybrid Plan / Strategy |
|---|---|---|---|---|---|
| [**oQ8e**](https://huggingface.co/splats/Qwen3.6-35B-A3B-oQ8e) | 8.0 | **8.00** | 35.1 GB | 0 | Full 8-bit Static |
| [**oQ6e**](https://huggingface.co/splats/Qwen3.6-35B-A3B-oQ6e) | 6.0 | **6.60** | 27.4 GB | 162 | 8bit×162 (DeltaNet Anchor) |
| [**oQ5e**](https://huggingface.co/splats/Qwen3.6-35B-A3B-oQ5e) | 5.0 | **5.67** | 23.6 GB | 352 | 8bit×162, 6bit×190 |
| [**oQ4e**](https://huggingface.co/splats/Qwen3.6-35B-A3B-oQ4e) | 4.0 | **4.70** | 19.7 GB | 317 | 8bit×162, 6bit×47, 5bit×108 |
| [**oQ3.5e**](https://huggingface.co/splats/Qwen3.6-35B-A3B-oQ3.5e) | 3.5 | **4.00** | 16.9 GB | 60 | 8bit×10, 5bit×10, 4bit×40 |

### 🛠 Technical Build Audit
* **Calibration:** Uses a 600-sample dataset across code, reasoning, and multi-turn conversations.
* **Sensitivity Proxy:** Qwen3.6-35B-A3B-oQ8e (Internal Baseline).
* **Optimization Floor:** Mandatory 8-bit protection is applied to the `lm_head`, DeltaNet heads, and the first 6 layers to keep the "Agentic Coding" features native.

## Model Highlights
* **Native MoE Scaling:** Optimized for the 256-expert architecture (8+1 activated).
* **Thinking Preservation:** Retains reasoning context in historical messages via DeltaNet stability.

---
**Acknowledgments:** These quants were built using the [oMLX](https://github.com/jundot/omlx) framework. The weight optimization process is based on the **GPTQ** algorithm by Frantar et al.

*Verified via Splats Lab Vault v2.8. These models are standard mlx-lm compatible and work with any app supporting MLX safetensors.*