Qwen3.6 35B A3B Claude 4.7 Opus OQ4e DWQ MC MTP Vision MLX

--- license: apache-2.0 language: - en library_name: mlx pipeline_tag: image-text-to-text base_model: - lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled base_model_relation: quantized datasets: - lordx64/reasoning-distill-opus-4-7-max-sft - open-r1/OpenR1-Math-220k - nvidia/OpenCodeReasoning - bigcode/self-oss-instruct-sc2-exec-filter-50k tags: - mlx - oq - imatrix - dwq - quantization - 4-bit - mtp - speculative-decoding - reasoning - chain-of-thought - code - math - qwen3.6 - mixture-of-experts - moe - image-text-to-text - vision --- # Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4e-DWQ-MC-MTP-Vision-MLX > ### ⭐ v2 — the best build of this model we ship > Two-stage **imatrix → DWQ** (reasoning, then math/code). Materially better on code than > the v1 repos: **HumanEval 90.2 %** (v1-stage: 84.8 %) · **LiveCodeBench 39.9 %** (32 %) · > **MBPP 75.4 %**. If you used any of the four `…-DWQ4-…` / `…-oQ4-…` v1 repos, use this instead. A **4-bit MLX quantization** of [`lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled`](https://huggingface.co/lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled) — **vision + text**, with an embedded **MTP** head for speculative decoding. > ⚠️ These are quantized weights. **All capability comes from the base model** — please > star/cite it first. This repo's contribution is the quantization recipe + MTP/vision > packaging and its fidelity/benchmark validation. ## Model lineage ``` Qwen/Qwen3.6-35B-A3B (Apache-2.0 base · 35B MoE · 256 experts · ~3B active · 262k ctx) └─ lordx64/…-Claude-4.7-Opus-Reasoning-Distilled (SFT distill of Claude Opus 4.7 reasoning) └─ THIS REPO: oQ4e (imatrix) → DWQ¹ reasoning → DWQ² math/code + MTP + vision ``` - **Architecture:** Qwen3.6-35B-A3B — MoE, 256 experts (8 routed + 1 shared), ~3B active params/token, up to **262,144-token** context. - **Base distillation (by [lordx64](https://huggingface.co/lordx64)):** SFT on ~7,800 chain-of-thought traces from **Claude Opus 4.7**, teaching explicit `<think>…</think>` reasoning. ## Quantization: `oQ4e` (imatrix) → two-stage `DWQ` Not a plain round-to-nearest 4-bit. Three steps: 1. **`oQ4e` — imatrix mixed precision.** oMLX's *enhanced* quantizer builds an importance matrix from calibration activations (sized for MoE expert coverage) and allocates bits by sensitivity. Base **4-bit affine, group size 64**, with sensitive tens...