Instructions to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-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 FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4
# Run inference directly in the terminal:
llama cli -hf FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

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 FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4
# Run inference directly in the terminal:
./llama-cli -hf FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

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 FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

Use Docker

docker model run hf.co/FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

LM Studio
Jan

vLLM

How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-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": "FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

Ollama
How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF with Ollama:
```
ollama run hf.co/FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4
```
Unsloth Desktop

How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

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:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF with Docker Model Runner:
```
docker model run hf.co/FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4
```

Lemonade

How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

Run and chat with the model

lemonade run user.Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF-NVFP4

List all available models

lemonade list

Hermes Agent

How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-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 FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

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 FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4

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 "FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF:NVFP4" \
  --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 NVFP4 No-MTP GGUF

Base Model

Qwen3.6-35B-A3B by Alibaba Qwen Team — a 35B-parameter Mixture-of-Experts (MoE) model with only 3B active parameters per token. Apache 2.0 licensed. Supports 131K+ context, tool use, and multilingual tasks across 100+ languages.

Why No MTP?

Qwen3.6-35B-A3B ships with Multi-Token Prediction (MTP) heads for speculative decoding. However, on MoE models like this one, MTP heads waste ~1-2 GB of VRAM with no measurable speed benefit — the bottleneck is expert routing through system RAM (when using --cpu-moe), not draft token verification. This build strips the MTP heads with --no-mtp to reclaim that VRAM for the KV cache and expert weights, resulting in better performance on 16GB cards.

Quantization

Format: NVIDIA FP4 (NVFP4) — 4-bit E2M1 values with E4M3 scaling per 16 values + FP32 tensor scale
BPW: 4.55 bits per weight
Size: 19.7 GB
Target hardware: NVIDIA Blackwell GPUs (RTX 50 series) — requires CUDA kernels at inference

Tested Settings (llama.cpp build 1324+, RTX 5060 Ti 16GB)

llama-cli -m qwen3.6-35b-a3b-nvfp4-nomtp.gguf \
  -ngl 99 --cpu-moe \
  --ctx-size 131072 \
  --flash-attn on \
  --cache-type-k q8_0 --cache-type-v q8_0 \
  -t 8 --temp 0.7 --top-k 20 --top-p 0.95

Performance Results

Metric	Result
Prompt processing	22.9 t/s
Token generation	29.1 t/s
Context	128K
KV Cache	Q8_0
Test prompt	"Tell me about superposition and quantum computing"
Output quality	Coherent, thorough, no hallucination, no repetition

Usage

llama.cpp CLI (text generation)

llama-cli -m qwen3.6-35b-a3b-nvfp4-nomtp.gguf   -ngl 99 --cpu-moe   -c 131072   --flash-attn on   --cache-type-k q8_0 --cache-type-v q8_0   -p "Your prompt here"

llama.cpp Server (API)

llama-server -m qwen3.6-35b-a3b-nvfp4-nomtp.gguf   -ngl 99 --cpu-moe   -c 131072   --flash-attn on   --cache-type-k q8_0 --cache-type-v q8_0   --host 0.0.0.0 --port 8080

Requirements

llama.cpp build 700+ with CUDA support
NVIDIA GPU with 16GB+ VRAM (tested on RTX 5060 Ti 16GB)
--cpu-moe flag required — routes MoE expert weights to system RAM while keeping attention on GPU
--flash-attn on recommended for memory efficiency at long context

Notes

Q8_0 KV cache recommended for quality — Q4_0 saves ~3 GB VRAM but loses precision
Model uses --cpu-moe because NVFP4 weights (~19.7 GB) exceed 16GB VRAM; experts stream from RAM at ~611 MB per token
For MXFP4_MoE variant (expert weights MXFP4, non-expert Q8_0), see MXFP4_MoE repo

License

Apache 2.0 (inherited from base model)

Downloads last month: 641

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

4-bit

Model tree for FreedomAISVR/Qwen3.6-35B-A3B-NVFP4-NoMTP-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Quantized

(839)

this model