Instructions to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-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 localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS # Run inference directly in the terminal: llama cli -hf localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS # Run inference directly in the terminal: llama cli -hf localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS # Run inference directly in the terminal: ./build/bin/llama cli -hf localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
Use Docker
docker model run hf.co/localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
- Llama new
- LM Studio
- Jan
- vLLM
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
- Ollama
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF with Ollama:
ollama run hf.co/localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
- Unsloth Desktop
- Pi
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF with Docker Model Runner:
docker model run hf.co/localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
- Lemonade
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
Run and chat with the model
lemonade run user.Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF-IQ4_XS
List all available models
lemonade list
- Hermes Agent
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-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 localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
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://127.0.0.1:9931/v1 hermes config set model.default localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS
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://127.0.0.1:9931/v1 \ --custom-model-id "localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF:IQ4_XS" \ --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"
Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn (GGUF)
35B MoE Qwen3.6-A3B trunk (3B active) + embedded NextN-MTP head, quantized for single-GPU inference.
- Trunk: IQ4_XS (imatrix-calibrated)
- MTP head: Q8_0 (NextN,
kv_only_nextn=true) - File size: ~18.3 GB
- Min VRAM: ~21 GB at 32K ctx with KV Q8/Q8
The MTP head is embedded inside the GGUF β no separate drafter file. Recent llama.cpp builds activate it via --spec-type draft-mtp.
Quick start (no spec decode)
llama-server -m Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn.gguf \
-ngl 999 -fa on -c 32768 --parallel 1 \
-ctk q8_0 -ctv q8_0 --kv-unified \
--host 0.0.0.0 --port 8080 --jinja
With speculative decoding (recommended)
Requires llama.cpp built from master after ggml-org/llama.cpp#22673:
llama-server -m Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn.gguf \
-ngl 999 -fa on -c 32768 --parallel 1 \
-ctk q8_0 -ctv q8_0 --kv-unified \
--spec-type draft-mtp \
--spec-draft-n-max 2 \
--spec-draft-p-min 0.0 \
--host 0.0.0.0 --port 8080 --jinja
For A3B MoE, smaller --spec-draft-n-max wins β accept rate decays faster with depth than dense models. n_max=2 is the sweet spot. For MoE at deeper chains (n>=3), --spec-draft-p-min 0.0 outperforms p_min=0.75 because per-step sampler overhead from top_k+softmax exceeds the accept-rate savings on this arch.
Benchmarks
Single-stream decode on a 24 GB consumer GPU (RTX 3090 Ti), CUDA build, full-GPU offload, FA on, N=512 generated tokens, 5-warm-run mean.
Production config (ctx=32K, KV Q8/Q8)
| config | decode tok/s |
|---|---|
| no spec (greedy) | ~120 (varies) |
--spec-type draft-mtp --spec-draft-n-max 2 --spec-draft-p-min 0.0 |
~200 (+67%) |
Smaller ctx variant (ctx=8192, KV q4_0/q4_0, p_min=0)
| n_max | tok/s |
|---|---|
| 1 | 189.5 |
| 2 | 198.7 (+24%) |
| 3 | 191.2 |
| 4 | 167.6 |
n_max=2 wins; deeper chains regress (MoE accept rate falls faster with depth).
Quant details
- Trunk weights:
IQ4_XScalibrated with an imatrix derived from a mixed-domain calibration set. - MTP head: kept at
Q8_0(NextN). Sensitive to precision. - KV cache:
Q8_0/Q8_0recommended.
llama.cpp requirements
- Build supporting Qwen3.6 NextN MTP (
LLM_ARCH_QWEN35MOE_MTP). Merged upstream in #22673. --spec-draft-p-min 0.75requires recent llama.cpp that honorsp_minon the DRAFT_MTP path.
Sister models
- Without imatrix: localweights/Qwen3.6-35B-A3B-MTP-IQ4_XS-Q8nextn-GGUF
- 27B dense variant: localweights/Qwen3.6-27B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF
Reference
- Base model: https://huggingface.co/Qwen/Qwen3.6-35B-A3B
- MTP architecture: NextN-style embedded prediction layer,
kv_only_nextn=true.
Apache 2.0 license.
- Downloads last month
- 429
4-bit
Model tree for localweights/Qwen3.6-35B-A3B-MTP-IMAT-IQ4_XS-Q8nextn-GGUF
Base model
Qwen/Qwen3.6-35B-A3B