Qwen3.6-35B-A3B-JANGTQ

Model Details

Quantization details, per tensor category

JANGTQ ("TurboQuant") stores routed-expert weights as indices into a small Lloyd-Max codebook with a per-row norm, after a randomized Hadamard rotation that concentrates the distribution so quantization error is uniform. At inference, the input is rotated once per layer (cheap fused Metal kernel) and dot products happen against the codebook centroids directly, so we never dequantize back to affine. Compared to affine 2-bit at the same bit budget, this gives better quality AND faster decode on the routed-expert MLP path.

Usage

JANGTQ requires our custom loader — stock mlx_lm.load() can't parse .tq_packed tensors. You need jang-tools (free, public): https://github.com/jjang-ai/jangq.

pip install mlx mlx-lm mlx-vlm
git clone https://github.com/jjang-ai/jangq && pip install -e ./jangq/jang-tools

Text

from jang_tools.load_jangtq import load_jangtq_model
from mlx_lm import generate

model, tokenizer = load_jangtq_model("OsaurusAI/Qwen3.6-35B-A3B-JANGTQ2")
print(generate(model, tokenizer,
               prompt="The capital of France is",
               max_tokens=64))

Image (VLM)

from jang_tools.load_jangtq_vlm import load_jangtq_vlm_model
from mlx_vlm import generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

path = "OsaurusAI/Qwen3.6-35B-A3B-JANGTQ2"
model, processor = load_jangtq_vlm_model(path)
config = load_config(path)

prompt = apply_chat_template(processor, config, "Describe this image.", num_images=1)
print(generate(model, processor, prompt, image="path/to/image.jpg", max_tokens=200))

Reasoning toggle

msgs = [{"role": "user", "content": "What is 17 × 23?"}]
# Reasoning OFF — pre-closed <think></think> block
prompt = tokenizer.apply_chat_template(msgs, add_generation_prompt=True,
                                       enable_thinking=False)
# Reasoning ON — model fills the <think> block
prompt = tokenizer.apply_chat_template(msgs, add_generation_prompt=True,
                                       enable_thinking=True)

Pass enable_thinking as a direct kwarg (the chat_template_kwargs={...} form only propagates on some tokenizer versions).

Video

The base model supports video via transformers and the bundle preserves video_preprocessor_config.json. mlx-vlm 0.4.4's prepare_inputs has no video path yet for qwen3_5_moe — the Python load_jangtq_vlm path wraps video via a custom processor for our test harness. For mainline mlx-vlm users, stick to image input; use upstream transformers for video.

Hardware notes

~12 GB on disk; expect ~12–14 GB resident after load, plus KV cache.

Benchmarks

Base-model reference (Qwen/Qwen3.6-35B-A3B, upstream, not this quant):

Independent JANGTQ-quant evaluation is tracked in the jang-tools repo and will land in future README revisions.

Citation

@misc{qwen2026qwen36,
  title  = {Qwen3.6-Plus: Towards Real World Agents},
  author = {Qwen Team},
  year   = {2026},
  url    = {https://qwen.ai/blog?id=qwen3.6}
}

License

Apache 2.0 — inherits from the base model.