Instructions to use kaitchup/Qwen3.8-27B-SLQ-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 kaitchup/Qwen3.8-27B-SLQ-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 kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S
# Run inference directly in the terminal:
llama cli -hf kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S
# Run inference directly in the terminal:
llama cli -hf kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

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 kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S
# Run inference directly in the terminal:
./build/bin/llama cli -hf kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

Use Docker

docker model run hf.co/kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

Llama new
LM Studio
Jan

vLLM

How to use kaitchup/Qwen3.8-27B-SLQ-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

Ollama
How to use kaitchup/Qwen3.8-27B-SLQ-GGUF with Ollama:
```
ollama run hf.co/kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S
```
Unsloth Desktop

How to use kaitchup/Qwen3.8-27B-SLQ-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

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": "kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use kaitchup/Qwen3.8-27B-SLQ-GGUF with Docker Model Runner:
```
docker model run hf.co/kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S
```

Lemonade

How to use kaitchup/Qwen3.8-27B-SLQ-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

Run and chat with the model

lemonade run user.Qwen3.8-27B-SLQ-GGUF-Q5_K_S

List all available models

lemonade list

Hermes Agent

How to use kaitchup/Qwen3.8-27B-SLQ-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 kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

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 kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use kaitchup/Qwen3.8-27B-SLQ-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S

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 "kaitchup/Qwen3.8-27B-SLQ-GGUF:Q5_K_S" \
  --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"

Subscribe to my newsletter · Support

Qwen3.8-27B-SLQ-GGUF

This is Qwen/Qwen3.8-27B, compressed with a customized version of SLQ (Statistically-Lossless Quantization) and assembled as GGUF. The search combines existing quantized donor weights and chooses a source separately for 498 complete matrices, including embeddings and the output head.

Choose one of three models:

Model	GGUF file	Active text weights (GB)	Complete file (GB)	Measured EAR@10 ↑
EAR98	Qwen3.8-27B-SLQ-EAR98-Q5_K_S.gguf	18.514	18.876	98.000383%
EAR98.5	Qwen3.8-27B-SLQ-EAR98.5-Q5_K_M.gguf	20.341	20.703	98.500187%
EAR99	Qwen3.8-27B-SLQ-EAR99-Q6_K.gguf	23.335	23.697	99.000026%

EAR targets: 98%, 98.5%, and 99%, selected using the BF16 reference's top 10 tokens.
Sizes: decimal GB (1 GB = 1,000,000,000 bytes). Active text weights include fixed text tensors and exclude MTP, metadata and alignment.
Embeddings / output head: Q4_K / Q8_0 for EAR98; Q4_K / BF16 for EAR98.5; Q6_K / BF16 for EAR99.
Each file retains 351,008,768 bytes of quantized MTP tensors from the UD-Q5_K_XL donor. MTP was disabled during evaluation. No vision tensors or multimodal projector are included.
Made by: The Kaitchup.
License: Apache 2.0.

The filename suffixes Q5_K_S, Q5_K_M, and Q6_K are Hub compatibility and dominant-precision-family labels for these custom SLQ allocations.

Method: SLQ paper · SLQ repository.

Candidate sources

The search considered UD-Q4_K_XL, UD-Q5_K_XL, UD-Q6_K_XL, Q4_0, Q8_0, and BF16 from unsloth/Qwen3.8-27B-GGUF, plus IQ3_S from ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF. Identical tensor payload alternatives were canonicalized. The final three models select no GSQ donor tensors; its candidates remained eligible during search.

Credit goes to the Qwen team for the base model, Unsloth for the GGUF donors, ISTA-DASLab for GSQ/RCO, and Michael Helcig, Eldar Kurtic and Dan Alistarh for SLQ. The base and donor repositories declare Apache 2.0 licensing; the full license is included below. Original copyright and attribution rights remain with their authors.

Precision by layer

EAR comparison

EAR means Expected Acceptance Rate. It measures the overlap between the original BF16 model's next-token probabilities and those of the compared model. For EAR@K, both distributions are separately renormalized over the BF16 reference's K most likely tokens. Full-vocabulary EAR uses all 248,320 token IDs. An EAR of 0.99 means 99% average probability overlap on that measured support; it does not mean 99% benchmark accuracy or identical generated answers.

Zoomable SVG

SLQ's “statistically lossless” objective concerns approximate fidelity, not identical numerical outputs. These releases meet their stated measured EAR@10 targets. The same calibration corpus guided model selection, so these values are calibration fidelity rather than an independent held-out benchmark. Statistical equivalence on downstream tasks has not been established for these releases.

Instructions: llama.cpp

Use a llama.cpp build with Qwen3.8 architecture support. Native text scoring and standalone GGUF parity were validated on an NVIDIA GH200 with llama.cpp commit 45451c366d4256f94fbc8845645e31a6b9155054. This validation did not cover image/video inference or speculative decoding.

Install the Hugging Face CLI, then download one file:

pip install -U huggingface_hub
hf download kaitchup/Qwen3.8-27B-SLQ-GGUF \
  Qwen3.8-27B-SLQ-EAR98-Q5_K_S.gguf --local-dir .

Start an OpenAI-compatible text server with the downloaded model:

llama-server \
  --model Qwen3.8-27B-SLQ-EAR98-Q5_K_S.gguf \
  --n-gpu-layers 99 \
  --ctx-size 8192 \
  --port 8080

To use EAR98.5 or EAR99, download the corresponding file from the table and change --model.

Send a chat request:

curl http://localhost:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{
    "messages": [{"role": "user", "content": "Is Earth smaller than Venus?"}],
    "max_tokens": 256
  }'