Instructions to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M

Use Docker

docker model run hf.co/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M

Ollama
How to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF with Ollama:
```
ollama run hf.co/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M
```
Unsloth Desktop

How to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M

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": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF with Docker Model Runner:
```
docker model run hf.co/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M
```

Lemonade

How to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.8-27B-Humanlike-Chat-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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 "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-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"

Rambles off into nonsense

by lothinx - opened 4 days ago

Discussion

lothinx

4 days ago

Set this up as described. I was previously using Qwen 3.8 Dark Scarlett, and decided to try this - so my prompts are already set up to work with Qwen. But with this one, I got a couple of paragraphs of good narrative fiction, then it gave me a paragraph of utter total nonsense, where it was basically just giving rambling filler text including bits of lorum ipsum, et ceteras, and even a "and forever amen" at the end of the rambling on an NSFW scene. Exact same settings took back to Dark Scarlett, and it's clear that it's this model that's the issue as Dark Scarlett doesn't do that with the same context, same settings, etc.

kvyb

LessThanThree AI org 3 days ago

Thanks for reporting this, especially for checking the same context and settings against Dark Scarlett. The output you describe isn't what I'd expect, and I'd like to reproduce it.

Could you share:

The exact model repo and checkpoint/quantization filename.
Your frontend and backend (vLLM, L.cpp?), including the backend version.
Your settings export or screenshot, plus the chat/instruct template.
Whether thinking was explicitly disabled, and how you disabled it.

Were you using the following settings, or did anything differ?

  API: Text Completion
  Backend: llama.cpp
  Context: 32768
  Response length: 512
  Temperature: 0.7
  Top P: 0.8
  Top K: 20
  Presence penalty: 1.5
  Repetition penalty: 1.0
  DRY: disabled
  Smoothing: disabled
  Manual stop strings: unset

If you're using llama.cpp, did your launch command include this?

  --chat-template-kwargs '{"enable_thinking":false}'

If you're comfortable sharing a short prompt and output excerpt that reproduces the issue, that would help too. Please remove anything private.

I'm asking for these details to reproduce your setup, not assuming you've configured anything incorrectly or that changing settings will fix it.

kvyb

LessThanThree AI org about 20 hours ago

Closed because we were unable to reproduce this behaviour and no further details were added by OP

kvyb changed discussion status to closed about 20 hours ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment