Qwen3.6-35B-A3B MLX

Community MLX conversions of Qwen/Qwen3.6-35B-A3B, produced and validated by PocketAI Model Lab. PocketAI did not train or fine-tune this model. This is not an official Qwen release, and no endorsement is implied.

This is a multimodal mixture-of-experts model with 35B total parameters, approximately 3B active parameters, 256 experts, and 8 routed experts per token.

Variants

All quantized modules use MLX affine quantization with group size 64. The 4-bit release intentionally retains 80 router and shared-expert gate modules at 8-bit precision; this is the converter's quality-preserving MoE layout. The converter reports effective stored precisions of 4.649 and 8.596 bits per weight for the 4-bit and 8-bit releases respectively.

Creative coding showcase

Each variant received the same prompt to create a colorful, single-file HTML voxel pagoda garden. The synchronized comparison below uses the same camera direction, 180-degree timing, elevation curve, and proportional push-in for all three versions.

Open or download the MP4

MLX generation performance

These are single-run generation measurements on a 128 GB Apple M5 Max MacBook Pro using mlx==0.32.0, mlx-vlm==0.6.8, batch size 1, thinking enabled, temperature 0.6, top-p 0.95, top-k 20, and seed 20260730. Generation speed excludes prompt prefill. Output lengths differ, so generation time should not be compared as though each variant emitted the same tokens. BF16 generating slightly faster than 8-bit is the measured result of this specific run.

All three original generations contained browser defects. The video uses minimally repaired copies while preserving the original benchmark outputs: 4-bit needed a correct instanced color attribute, 8-bit needed a non-terminating path loop and numeric color parsing corrected, and BF16 needed its broken inline orbit controller replaced. Exact settings, raw measurements, prompt text, and repair status are recorded in benchmarks/creative-voxel-pagoda.json.

Download and load

Install the validated runtime on an Apple Silicon Mac:

python -m pip install "mlx==0.32.0" "mlx-vlm==0.6.8"

Download only the desired variant and load its local subfolder:

from pathlib import Path

from huggingface_hub import snapshot_download
from mlx_vlm import generate, load
from mlx_vlm.prompt_utils import apply_chat_template

repo_id = "PocketAiHub/Qwen3.6-35B-A3B-MLX"
variant = "4bit"  # "4bit", "8bit", or "bf16"

snapshot = Path(
    snapshot_download(
        repo_id,
        allow_patterns=[f"{variant}/*"],
    )
)
model, processor = load(str(snapshot / variant))

prompt = apply_chat_template(
    processor,
    model.config,
    "Explain why seasons occur.",
    num_images=0,
    enable_thinking=False,
)
result = generate(
    model,
    processor,
    prompt,
    max_tokens=256,
    temperature=0.0,
    enable_thinking=False,
)
print(result.text)

For vision input, pass an image path to mlx_vlm.generate and build the prompt with num_images=1.

Reproducibility and validation

• Official source: Qwen/Qwen3.6-35B-A3B
• Pinned source revision: 995ad96eacd98c81ed38be0c5b274b04031597b0
• Converter: mlx-vlm==0.6.8
• Base dtype: BF16
• Quantization: MLX affine, group size 64
• Preserved MoE layout: 256 experts, 8 routed experts per token
• Deterministic text smoke: exact POCKETAI_OK
• Deterministic image smoke: exact dominant color red
• Full PocketAI Model Lab suite: 106/106 tests
• Every uploaded variant includes an artifact-manifest.json with exact file sizes and SHA-256 hashes.

The standalone MTP draft weights from the source checkpoint are not included; these are standard MLX generation artifacts, not a speculative-decoding MTP bundle.

The checks above establish artifact integrity, strict runtime loading, basic text generation, and basic image understanding. They are not a broad benchmark or a guarantee of correctness for every prompt, context length, or serving configuration.

License and attribution

These conversions retain the original model's Apache 2.0 license. See LICENSE and the official Qwen model card.

• PocketAI Model Lab: https://github.com/PocketAIHub/pocketai-model-lab