Instructions to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS
# Run inference directly in the terminal:
./llama-cli -hf SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

Use Docker

docker model run hf.co/SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

LM Studio
Jan

vLLM

How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-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": "SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

Ollama
How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF with Ollama:
```
ollama run hf.co/SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS
```

Unsloth Studio

How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF to start chatting

How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

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": "SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF with Docker Model Runner:
```
docker model run hf.co/SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS
```

Lemonade

How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

Run and chat with the model

lemonade run user.Qwen3.8-27B-Pym-IQ2_XXS-GGUF-IQ2_XXS

List all available models

lemonade list

Hermes Agent

How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

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 SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS

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 "SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF:IQ2_XXS" \
  --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"

Qwen3.8-27B-Pym-IQ2_XXS

A ~16 GB imatrix-calibrated, mixed-precision GGUF of Qwen3.8-27B (a qwen35 hybrid SSM+attention architecture) — SGLabs' first dense-model Pym quant.

Base model: Qwen/Qwen3.8-27B — a multimodal (image-text-to-text), 27B dense model with 256K context, agentic-coding and reasoning strengths, and a native MTP head.

This quant: dense FFN to 2–3 bits; attention, SSM, norms, embeddings, and the MTP head preserved at Q8 (so speculative decoding stays on). Runs on llama.cpp — AMD (ROCm) and Apple Silicon. No CUDA required.

Precision map

ffn_gate, ffn_up → IQ2_XXS
ffn_down → IQ3_XXS
attention · SSM · norms · embeddings · output · MTP block → Q8_0

Usage

# with MTP speculative decoding (recommended):
llama-server -m Qwen3.8-27B-Pym-IQ2_XXS.gguf -ngl 999 -c 32768 \
  --spec-type draft-mtp --spec-draft-n-max 2 -np 1

File / compatibility


File	`Qwen3.8-27B-Pym-IQ2_XXS.gguf`
Size	15.99 GB (14.9 GiB) · 4.68 BPW
Architecture	`qwen35` · 65 blocks (64 + MTP)

Mixed-precision quant: the filename carries the dominant standard token (IQ2_XXS) for general compatibility; loaders requiring a uniform general.file_type may report it as custom.

Quantized by SGLabs.

Downloads last month: 334

GGUF

Model size

27B params

Architecture

qwen35

Hardware compatibility

2-bit

Model tree for SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF

Base model

Qwen/Qwen3.8-27B

Quantized

(809)

this model

Collection including SGLabs/Qwen3.8-27B-Pym-IQ2_XXS-GGUF

Pym

Collection

Aggressive mixed-precision GGUF quants — shrink models to a fraction of their size, keep their edge and speed. Runs on llama.cpp (AMD/Apple too). • 2 items • Updated 10 days ago