Instructions to use prithivMLmods/Qwen3.5-27B-MTP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Qwen3.5-27B-MTP-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="prithivMLmods/Qwen3.5-27B-MTP-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("prithivMLmods/Qwen3.5-27B-MTP-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use prithivMLmods/Qwen3.5-27B-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 prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf prithivMLmods/Qwen3.5-27B-MTP-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 prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf prithivMLmods/Qwen3.5-27B-MTP-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 prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use prithivMLmods/Qwen3.5-27B-MTP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Qwen3.5-27B-MTP-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": "prithivMLmods/Qwen3.5-27B-MTP-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/prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M

SGLang

How to use prithivMLmods/Qwen3.5-27B-MTP-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "prithivMLmods/Qwen3.5-27B-MTP-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Qwen3.5-27B-MTP-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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "prithivMLmods/Qwen3.5-27B-MTP-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Qwen3.5-27B-MTP-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use prithivMLmods/Qwen3.5-27B-MTP-GGUF with Ollama:
```
ollama run hf.co/prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M
```

Unsloth Studio

How to use prithivMLmods/Qwen3.5-27B-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 prithivMLmods/Qwen3.5-27B-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 prithivMLmods/Qwen3.5-27B-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 prithivMLmods/Qwen3.5-27B-MTP-GGUF to start chatting

How to use prithivMLmods/Qwen3.5-27B-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 prithivMLmods/Qwen3.5-27B-MTP-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": "prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use prithivMLmods/Qwen3.5-27B-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 prithivMLmods/Qwen3.5-27B-MTP-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 prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use prithivMLmods/Qwen3.5-27B-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 prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M

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 "prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M" \
  --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 prithivMLmods/Qwen3.5-27B-MTP-GGUF with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M
```

Lemonade

How to use prithivMLmods/Qwen3.5-27B-MTP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull prithivMLmods/Qwen3.5-27B-MTP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-27B-MTP-GGUF-Q4_K_M

List all available models

lemonade list

Qwen3.5-27B-MTP-GGUF

Qwen3.5-27B from Alibaba's Qwen team is a 27B-parameter dense (non-MoE) multimodal transformer model—the only full-weight, non-MoE model in the Qwen3.5 Medium Series—featuring 64 layers, 5120 hidden dimension, 248K vocabulary for 201+ languages, native multimodal input (text + images + video via early fusion), and a massive 256K native context window extensible to 1M+ tokens via YaRN. Released February 24, 2026 under Apache 2.0, it achieves 72.4% on SWE-bench Verified (matching GPT-5 mini), 87.8% GPQA Diamond, 66.1% BFCL-V4 for native tool calling, and excels at agentic coding, frontend development, repository-level code comprehension, and complex reasoning while running on 22GB VRAM (Mac M-series, single RTX 4090) with simple deployment free of MoE routing overhead. Its strengths include native multimodal chat, long-context document processing, structured JSON outputs, fine-tuning for specialized domains, and Ollama/vLLM/llama.cpp support, making it ideal for production multimodal assistants combining image understanding with grounded text reasoning at efficient scale.

Multi-Token Prediction (MTP) GGUF is a specialized GGUF model file format extension that integrates speculative decoding directly into the model weights to significantly accelerate local inference. Unlike traditional speculative decoding which requires a separate, smaller "draft" model, MTP GGUF files include additional output heads within the main model architecture that predict multiple future tokens in a single forward pass.

Model Files

File Name	Quant Type	File Size	File Link
Qwen3.5-27B.BF16.gguf	BF16	54.7 GB	Download
Qwen3.5-27B.F16.gguf	F16	54.7 GB	Download
Qwen3.5-27B.Q2_K.gguf	Q2_K	10.9 GB	Download
Qwen3.5-27B.Q3_K_L.gguf	Q3_K_L	14.6 GB	Download
Qwen3.5-27B.Q3_K_M.gguf	Q3_K_M	13.5 GB	Download
Qwen3.5-27B.Q3_K_S.gguf	Q3_K_S	12.3 GB	Download
Qwen3.5-27B.Q4_0.gguf	Q4_0	15.7 GB	Download
Qwen3.5-27B.Q4_K_M.gguf	Q4_K_M	16.8 GB	Download
Qwen3.5-27B.Q4_K_S.gguf	Q4_K_S	15.8 GB	Download
Qwen3.5-27B.Q5_0.gguf	Q5_0	19 GB	Download
Qwen3.5-27B.Q5_K_M.gguf	Q5_K_M	19.5 GB	Download
Qwen3.5-27B.Q5_K_S.gguf	Q5_K_S	19 GB	Download
Qwen3.5-27B.Q6_K.gguf	Q6_K	22.4 GB	Download
Qwen3.5-27B.Q8_0.gguf	Q8_0	29 GB	Download
Qwen3.5-27B.mmproj-bf16.gguf	mmproj-bf16	931 MB	Download
Qwen3.5-27B.mmproj-f16.gguf	mmproj-f16	931 MB	Download
Qwen3.5-27B.mmproj-q8_0.gguf	mmproj-q8_0	629 MB	Download

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):

Downloads last month: 409

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for prithivMLmods/Qwen3.5-27B-MTP-GGUF

Base model

Qwen/Qwen3.5-27B

Quantized

(224)

this model

Collection including prithivMLmods/Qwen3.5-27B-MTP-GGUF

MTP Qwen 3.5/3.6 Stable

Collection

Collection of Qwen 3.5/3.6 MTP Featuring GGUF • 5 items • Updated about 16 hours ago • 2