Instructions to use underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp with MLX:

# Make sure mlx-vlm is installed
# pip install --upgrade mlx-vlm

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp")
config = load_config("underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

⚠️ Read this before downloading: enabling Lightning MTP makes this model slower

Mixed-precision quant of llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved, produced with oQ (oMLX v0.6.1). The MTP head is preserved so Lightning MTP can be enabled — but on this model, enabling it actually reduces generation speed instead of improving it.

TL;DR: If you don't need to test MTP on this specific model, don't download it. It's slower with Lightning MTP on, and no faster than other oQ4e quants with it off.

The MTP problem — measured, not guessed

Two oMLX benchmark runs on the same machine (M4 10-core, 32 GB), identical settings except mtp_enabled:

Setting	1k TG tok/s	4k TG tok/s	TTFT (4k)	Peak mem (4k)
Lightning MTP on (`mtp_enabled: true`)	41.2	35.1	8,879 ms	22.1 GB
MTP off (`mtp_enabled: false`)	39.2	37.6	8,817 ms	20.7 GB

At 1k context, MTP on wins by ~2 tok/s; at 4k context, MTP off is ~7% faster and uses ~1.4 GB less memory. In real use (longer contexts), MTP on is the slower option.

This is not unique to this quant: the exact same regression is documented upstream in jundot/omlx#2150 — on Qwen3.6-35B-A3B (MoE), Lightning MTP is 8–12% slower than the old fixed depth-1 MTP at every context length tested. The depth-k draft controller's cost model was tuned for dense backbones, and each extra verify token in this fine-grained MoE (256 experts) pulls a nearly disjoint routed-expert set — so the extra verification work isn't amortized. The issue also notes Lightning MTP is completely inactive during continuous batching (2×/4×), so batching speedups in the benchmark UI reflect plain batching, not MTP.

What this model is

This is an oQ4e (mixed-precision, ~4.6 bits-per-weight) MLX quant of the Heretic-abliterated Qwen3.6-35B-A3B with all 19 MTP tensors preserved — the first MTP-preserved MLX version of this model line, so anyone who wants to test Lightning MTP behavior on Qwen3.5/3.6 MoE can do so.

Base: Qwen/Qwen3.6-35B-A3B — 35B total / 3B activated, 256 experts (8 routed + 1 shared), 262k native context
Uncensored: Heretic v1.3.0 + MPOA abliteration — 10/100 refusals vs 83/100 original, KL divergence 0.0015
MTP: All 19 MTP tensors intact (mtp.layers.*, mtp.fc, mtp.norm, …)
Vision: Qwen3.6 VL tower intact — image + video input works (needs vlm_mtp_enabled for MTP on vision)

What is oQ?

Unlike uniform 4-bit quantization, oQ is a data-driven mixed-precision quantizer that calibrates per-layer sensitivity and allocates bits where they matter most. Critical layers (embeddings, LM head, the most sensitive transformer layers) are automatically promoted to 8-bit, while less sensitive layers stay at 4-bit. Typical result: ~4.6 bits-per-weight.

Benchmarked on Qwen3.5-35B-A3B (oMLX project):

Benchmark	mlx-lm 4-bit	oQ4
MMLU (300)	79.7%	83.3%
TruthfulQA (300)	87.7%	88.0%
HumanEval (full)	87.2%	85.4%
MBPP (300)	71.7%	74.3%

Quick start

# oMLX — MTP off (recommended for this model)
omlx serve --model underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp

# To test Lightning MTP anyway (expect *slower* generation, see above)
omlx serve --model underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp \
  --set mtp_enabled=true

Feedback welcome

If you measure Lightning MTP behavior on this model on different hardware (M3 Ultra, M4 Max, M5…) or a newer oMLX build, please post the benchmark link in the Community Discussion. The upstream issue is jundot/omlx#2150.

License

Apache 2.0, inherited from base model.

Downloads last month: 580

Safetensors

Model size

36B params

Tensor type

U32

BF16

MLX

Hardware compatibility

4-bit

Model tree for underlotus/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved-oQ4e-mtp

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-Native-MTP-Preserved

Quantized

(16)

this model