Instructions to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF",
	filename="Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-Balanced.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

Use Docker

docker model run hf.co/mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

LM Studio
Jan
Ollama
How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with Ollama:
```
ollama run hf.co/mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16
```

Unsloth Studio

How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF to start chatting

How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

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 mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

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 "mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

Docker Model Runner
How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16
```

Lemonade

How to use mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF:F16

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-GGUF-F16

List all available models

lemonade list

⚡ Each donation = another big MoE quantized

I host 30+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory) — enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant.
If APEX quants are useful to you, your support directly funds those bigger runs.

🎉 Patreon (Monthly) | ☕ Buy Me a Coffee | ⭐ GitHub Sponsors

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled — APEX-MTP GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of lordx64/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled, with the MTP (multi-token prediction) head bundled for in-the-box self-speculative decoding.

Brought to you by the LocalAI team | APEX Project | Technical Report

What's different from the plain APEX repo?

These GGUFs bundle the model's MTP (multi-token prediction) head alongside the trunk in a single file, courtesy of llama.cpp PR #22673. With a recent llama.cpp (>= commit 255582687) you can enable self-speculative decoding using just this one file — no separate draft model needed:

llama-server -m Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-MTP-I-Balanced.gguf --draft-mtp

The non-MTP version is still available at mudler/Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-APEX-GGUF — slightly smaller, but no self-spec.

File sizes

Each quant is ~2.5% larger than its non-MTP counterpart (one extra transformer-block worth of weights, no embedding duplication since MTP shares the trunk's embed_tokens).

MTP draft head precision

The bundled MTP head (blk.40.* including the nextn.* projection + norms) is quantized to Q8_0 (near-lossless) on every tier except I-Nano. I-Nano keeps the trunk-tier precision on the MTP block (Q3_K routed experts, Q4_K attention) but pins blk.40.nextn.eh_proj to Q4_K — see the explainer below.

This keeps draft accuracy high (important for spec-decode acceptance rate) at a modest ~1 GB cost per file vs. trunk-tier precision.

Why the MTP head doesn't use imatrix

llama-imatrix runs normal forward passes that only activate the trunk (blk.0..blk.39). The MTP head only fires during --draft-mtp spec decoding, so its tensors get no imatrix activation data. We work around this by quantizing the MTP head with static K-quant / Q8_0 which doesn't require imatrix.

(A patch to llama-imatrix that records MTP activations during collection is in progress at mudler/llama.cpp#mtp-imatrix — once upstream this will let us push the drafter to lower bit-widths cleanly.)

What is APEX?

APEX is a MoE-aware mixed-precision quantization strategy. Per-tensor-role gradient: routed experts compress hardest, shared experts kept high (always active), attention/Mamba uniform; 5+5 symmetric edge gradient across the 40 trunk layers + MTP layer 40 at edge precision. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).

See the APEX project for full details.