Downloads · 30 days
38
3% of all-time downloads
Litwein/Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4-MTP-Vision-MLX
Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4-MTP-Vision-MLX is a image-text-to-text model from Litwein. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
[](https://huggingface.co/Litwein/Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4e-DWQ-MC-MTP-Vision-MLX)
Downloads · 30 days
38
3% of all-time downloads
All-time downloads
1.2K
Public
Parameters
36B
21.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors21.6 GB · 100%
How the weights are stored.
U3235.5B · 99%
From the Hugging Face model README
⚠️ Superseded — use v2 instead
👉
Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4e-DWQ-MC-MTP-Vision-MLXv2 is a two-stage imatrix → DWQ build (reasoning, then math/code) of the same base. It is materially better on code — HumanEval 90.2 % (this v1 line: 84.8 %) · LiveCodeBench 39.9 % (v1: 32 %) · MBPP 75.4 % — at the same size class, same MTP + vision packaging.
This v1 repo is kept for reproducibility only. New users should download v2.
A 4-bit MLX quantization (oQ) of
lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled — vision + text, with MTP speculative decoding.
This is a vision-language build of the reasoning-distilled Qwen3.6-35B-A3B, packaged for fast local inference on Apple Silicon with an embedded Multi-Token-Prediction (MTP) head for speculative decoding.
⚠️ These are quantized weights. All capability comes from the base model
lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled— please star/cite it first. This repo's contribution is the quantization + MTP/vision packaging and its fidelity/speed validation.
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 distillation of Claude Opus 4.7 reasoning)
└─ THIS REPO: oQ 4-bit MLX + MTP + vision
<think>…</think> reasoning. Attention-only LoRA (r=16) via Unsloth + TRL.This is an oQ4 quant produced by oMLX's built-in oq quantizer —
sensitivity-based dynamic mixed precision. Each layer is measured for its impact on the
output and assigned 4, 5, 6 or 8 bits accordingly; the most sensitive projections keep
more bits, the rest go to 4-bit.
| Scheme | affine mixed 4/5/6/8-bit, group size 64 (sensitivity-assigned per layer) |
| Effective size | ~4.9 bits/weight |
| Calibration | oMLX auto_proxy_sensitivity proxy pass over the base weights |
| Tooling | oMLX oq (preserve_mtp=true) |
Mixed precision spends extra bits on sensitive layers; the sibling DWQ4 repos reach the same task quality at a smaller, uniform 4-bit footprint (see Evaluation).
Two kinds of numbers below: quant-fidelity metrics measured on this quant, and capability benchmarks inherited from the bf16 base (a 4-bit quant preserves — does not create — capability; the fidelity metrics show how little was lost).
| Metric | This model | Notes |
|---|---|---|
| Gradeable math (10 short-answer problems) | 9 / 10¹ | arithmetic, GCD, algebra, calculus, combinatorics — all complete within budget |
Code (4 tasks, exec-checked) | 4 / 4 | RLE, median, balanced-brackets, int→Roman |
| Perplexity | not reported — plain mlx_lm mis-loads oq's 5-bit layers offline; compared via tasks below | |
| Decode speed (MTP on, M4 Pro 48 GB) | ~50–53 tok/s | multi-token-prediction speculative decoding (measured) |
| MTP draft acceptance | ~40–64 % | content-dependent |
¹ The single miss is a grader formatting artifact on a prime-factorization prompt (7×13 vs 7 and 13), not a reasoning error.
Note on long-form math. This is a reasoning model that routinely emits 8,000+ tokens of
<think>on olympiad problems. Fixed-budget pass/fail on such problems is token-budget-limited, not quantization-limited — every 4-bit and 8-bit level behaves the same. Give it a largemax_tokens(32k) for hard problems.
Reported by the base model lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled via lm-evaluation-harness; listed here as a
capability reference for the family, not re-measured on this quant.
| Benchmark | Base (bf16) |
|---|---|
| GSM8K (8-shot CoT) | 84.3 % |
| MMLU-Pro (5-shot) | 74.9 % |
| MMLU-Pro · Math | 83.6 % |
| MMLU-Pro · Physics | 81.0 % |
| MMLU-Pro · Computer Science | 79.0 % |
| Repo | Quant | Vision | Size | Best for |
|---|---|---|---|---|
…-DWQ4-MTP-Vision-MLX | DWQ uniform 4-bit | ✓ | ~21 GB | smallest+fastest, multimodal |
…-DWQ4-MTP-MLX | DWQ uniform 4-bit | – | ~19 GB | smallest+fastest, text only |
…-oQ4-MTP-Vision-MLX | oq mixed 4–8-bit | ✓ | ~22 GB | mixed-precision, multimodal |
…-oQ4-MTP-MLX | oq mixed 4–8-bit | – | ~21 GB | mixed-precision, text only |
TL;DR: the DWQ builds are smaller, a touch faster, and match the oQ builds on task quality — distillation lets uniform 4-bit keep up with mixed precision. oQ builds spend extra bits on sensitive layers (a more conservative, classic dynamic quant).
These are MLX weights (Apple Silicon). The tested serving path is oMLX, which supports this model's native MTP speculative decoding and vision out of the box.
This repo includes the vision tower (vision_tower.*, bf16) — it accepts images/video as well as text.
1. Place the folder in your oMLX models directory:
# after downloading this repo:
mv Qwen3.6-35B-A3B-Claude-4.7-Opus-oQ4-MTP-Vision-MLX ~/.omlx/models/
2. Enable MTP for this model (one-time), then call the OpenAI-compatible API:
curl -X PUT http://127.0.0.1:8003/admin/api/models/qwen3.6-35b-a3b-claude-4.7-opus-oq4-mtp-vision-mlx/settings \
-H "Authorization: Bearer sk-local" -H "Content-Type: application/json" \
-d '{"mtp_enabled": true}'
curl -X POST http://127.0.0.1:8003/v1/chat/completions \
-H "Authorization: Bearer sk-local" -H "Content-Type: application/json" \
-d '{"model": "qwen3.6-35b-a3b-claude-4.7-opus-oq4-mtp-vision-mlx",
"messages": [{"role": "user", "content": "Prove there are infinitely many primes."}],
"max_tokens": 8000, "temperature": 0.6}'
The oq mixed-precision (4–8-bit) layout is built for oMLX; stock mlx-lm does not reliably reconstruct the 5-bit layers, so run this build through oMLX.
MTP speculative decoding needs an MTP-aware runtime — oMLX (tested), or mlx-lm with PR #990.
temperature 0.6, top_p 0.95, top_k 20. For hard reasoning set max_tokens ≥ 32000 — the
model thinks in explicit <think>…</think> blocks and can be long.
<think> blocks — budget tokens accordingly.lordx64/reasoning-distill-opus-4-7-max-sft
— ~7,800 Claude Opus 4.7 reasoning conversations.mlx / mlx-vlm — the MLX runtime that oMLX's oq quantizer is built on.oq quantizer, MTP/vision serving runtime, and OpenAI-compatible API.Apache-2.0, inherited from the base model and Qwen3.6-35B-A3B.
@misc{qwen36_a3b_2026, title={Qwen3.6-35B-A3B}, author={Qwen Team}, year={2026},
howpublished={\url{https://huggingface.co/Qwen/Qwen3.6-35B-A3B}} }
@misc{lordx64_qwen36_distill_2026,
title={Qwen3.6-35B-A3B distilled from Claude Opus 4.7 reasoning}, author={lordx64}, year={2026},
howpublished={\url{https://huggingface.co/lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled}} }