Instructions to use maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp with MLX:

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

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-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 "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-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 "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-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 maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-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 "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-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 "maxlaurence/Qwopus3.6-35B-A3B-v1-oQ4-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"

Qwopus3.6-35B-A3B-v1-oQ4-mtp (oMLX build)

Local oMLX build of Jackrong/Qwopus3.6-35B-A3B-v1 — Qwen3.6 35B-A3B MoE (~3B active per token), text-only.

How it was built

Trunk: faithfully re-quantized from the bf16 source to oMLX oQ4 — 4-bit / group-size 64, with every MoE router gate (mlp.gate, mlp.shared_expert_gate) at 8-bit, matching the proven stamsam oQ4-MTP recipe. ~4.649 bits/weight.
MTP head: Qwopus's own MTP head is byte-identical to the unsloth base Qwen3.6-35B-A3B head, which drafts at 0% acceptance once quantized on this MoE (the known quantized-MTP collapse). This build therefore uses the distilled MTP head from Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled (stamsam), which is quantization-robust and achieves ~77% draft acceptance on this trunk.
The draft head only proposes tokens; the Qwopus trunk verifies and accepts/rejects each one, so generated content is 100% Qwopus — the head only affects speed.

Verified

Loads in oMLX as qwen3_5_moe (batched engine), native MTP patch (PR 990) active, MTP acceptance ~77% (60/78 measured). Trunk-only generation ~91 tok/s on M4 Max 48 GB.

Registered with mtp_enabled: true in ~/.omlx/model_settings.json. Build scripts: ~/.omlx-build/ (convert_qwopus.py, build_mtp.py, assemble_omlx.py, install_omlx.py).

Downloads last month: 15

Safetensors

Model size

35B params

Tensor type

BF16

U32

MLX

Hardware compatibility

4-bit