Instructions to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF",
	filename="Qwen3.6-VL-REAP-26B-A3B-text-IQ4_XS.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

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 keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

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 keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "keithnull/Qwen3.6-VL-REAP-26B-A3B-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": "keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

Ollama
How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with Ollama:
```
ollama run hf.co/keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-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 keithnull/Qwen3.6-VL-REAP-26B-A3B-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 keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF to start chatting

Pi new

How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

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": "keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

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 keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with Docker Model Runner:
```
docker model run hf.co/keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M
```

Lemonade

How to use keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.6-VL-REAP-26B-A3B-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.6-VL-REAP-26B-A3B — GGUF

GGUF quantizations of atbender/Qwen3.6-VL-REAP-26B-A3B, a REAP-pruned variant of Qwen3.6-VL. Both the language model (text quants) and the vision tower (mmproj) are included - drop the mmproj alongside any text quant for full multimodal (image + text) inference.

Files

File	Quant	Size
`Qwen3.6-VL-REAP-26B-A3B-text-Q4_K_M.gguf`	Q4_K_M	~15 GB
`Qwen3.6-VL-REAP-26B-A3B-text-IQ4_XS.gguf`	IQ4_XS	~14 GB
`Qwen3.6-VL-REAP-26B-A3B-text-Q3_K_S.gguf`	Q3_K_S	~11 GB
`mmproj-REAP-26B-F16.gguf`	F16 (vision tower)	~860 MB

Quality vs bf16 (wikitext-2-raw, llama.cpp perplexity)

Each text quant was scored against the bf16 reference using llama-perplexity on the wikitext-2-raw test split (580 chunks, n_ctx=512, ~297k tokens). Bench run on a single RTX PRO 6000 (Blackwell, 96 GB).

Quant	PPL	ΔPPL vs bf16	Mean KLD	Top-1 token agree
bf16 (reference)	9.2369	—	0	100%
Q4_K_M	9.3858	+1.62%	0.0449	90.41%
IQ4_XS	9.4293	+2.08%	0.0457	90.03%
Q3_K_S	10.4822	+13.51%	0.1626	81.85%

On Apple Silicon (llama.cpp, q8_0 KV cache): Q4_K_M had the best speed/quality trade-off across both standalone code-gen and agentic tasks. Q3_K_S held up reasonably well on quality at a smaller footprint, and IQ4_XS produced correct outputs but ran noticeably slower in the same harness. Your mileage may vary depending on your hardware and setup.

Usage

Text-only

llama-cli -m Qwen3.6-VL-REAP-26B-A3B-text-Q4_K_M.gguf -cnv

Vision-language (multimodal)

The vision tower is loaded via --mmproj. Both llama-mtmd-cli (one-shot image+prompt) and llama-server (OpenAI-compatible HTTP server with image input) are supported.

One-shot CLI:

llama-mtmd-cli \
    -m Qwen3.6-VL-REAP-26B-A3B-text-Q4_K_M.gguf \
    --mmproj mmproj-REAP-26B-F16.gguf \
    --image path/to/photo.jpg \
    -p "Describe this image."

Server (OpenAI-compatible /v1/chat/completions with image_url):

llama-server \
    -m Qwen3.6-VL-REAP-26B-A3B-text-Q4_K_M.gguf \
    --mmproj mmproj-REAP-26B-F16.gguf \
    --port 8080

Then send a chat-completions request with an image_url content part (data URL or http URL) — the server routes it through the mmproj automatically. Capability is advertised as multimodal on the /v1/models endpoint when --mmproj is set.

Notes on the vision tower

Converted from atbender's source vision encoder weights (BF16) to GGUF F16 via llama.cpp's convert_hf_to_gguf.py --mmproj pipeline.
Validated end-to-end with llama-mtmd-cli on two test images (a real-world product photo and a music album scan); both produced accurate descriptions including readable on-image text, matching expectations from the bf16 reference.
F16 was kept (not quantized further) because the vision tower is small (~860 MB) and quality-sensitive; the marginal disk savings of FP8/Q8 don't justify the risk of degrading image grounding.

Acknowledgements

Base model (REAP-pruned): atbender/Qwen3.6-VL-REAP-26B-A3B
Upstream architecture: Qwen3-VL (Alibaba)
REAP pruning method: Cerebras Research
Quantized with llama.cpp

License inherited from the base model (Apache 2.0).

Downloads last month: 3,080

GGUF

Model size

27B params

Architecture

qwen35moe

Hardware compatibility

3-bit

4-bit

Model tree for keithnull/Qwen3.6-VL-REAP-26B-A3B-GGUF

Base model

Qwen/Qwen3.6-35B-A3B

Finetuned

atbender/Qwen3.6-VL-REAP-26B-A3B

Quantized

(2)

this model