Instructions to use basecompute/Qwen3.8-27B-BaseQuant-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use basecompute/Qwen3.8-27B-BaseQuant-V1 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 basecompute/Qwen3.8-27B-BaseQuant-V1
# Run inference directly in the terminal:
llama cli -hf basecompute/Qwen3.8-27B-BaseQuant-V1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf basecompute/Qwen3.8-27B-BaseQuant-V1
# Run inference directly in the terminal:
llama cli -hf basecompute/Qwen3.8-27B-BaseQuant-V1

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 basecompute/Qwen3.8-27B-BaseQuant-V1
# Run inference directly in the terminal:
./llama-cli -hf basecompute/Qwen3.8-27B-BaseQuant-V1

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 basecompute/Qwen3.8-27B-BaseQuant-V1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf basecompute/Qwen3.8-27B-BaseQuant-V1

Use Docker

docker model run hf.co/basecompute/Qwen3.8-27B-BaseQuant-V1

LM Studio
Jan

vLLM

How to use basecompute/Qwen3.8-27B-BaseQuant-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "basecompute/Qwen3.8-27B-BaseQuant-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "basecompute/Qwen3.8-27B-BaseQuant-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/basecompute/Qwen3.8-27B-BaseQuant-V1

Ollama
How to use basecompute/Qwen3.8-27B-BaseQuant-V1 with Ollama:
```
ollama run hf.co/basecompute/Qwen3.8-27B-BaseQuant-V1
```
Unsloth Desktop

How to use basecompute/Qwen3.8-27B-BaseQuant-V1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf basecompute/Qwen3.8-27B-BaseQuant-V1

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": "basecompute/Qwen3.8-27B-BaseQuant-V1"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use basecompute/Qwen3.8-27B-BaseQuant-V1 with Docker Model Runner:
```
docker model run hf.co/basecompute/Qwen3.8-27B-BaseQuant-V1
```

Lemonade

How to use basecompute/Qwen3.8-27B-BaseQuant-V1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull basecompute/Qwen3.8-27B-BaseQuant-V1

Run and chat with the model

lemonade run user.Qwen3.8-27B-BaseQuant-V1-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use basecompute/Qwen3.8-27B-BaseQuant-V1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf basecompute/Qwen3.8-27B-BaseQuant-V1

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 basecompute/Qwen3.8-27B-BaseQuant-V1

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use basecompute/Qwen3.8-27B-BaseQuant-V1 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf basecompute/Qwen3.8-27B-BaseQuant-V1

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 "basecompute/Qwen3.8-27B-BaseQuant-V1" \
  --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-BaseQuant-V1

Quantized builds of Qwen/Qwen3.8-27B in three sizes. On held-out text, each one is closer to the BF16 model than the unsloth dynamic quant of the same size.

Size	GGUF (llama.cpp)	baseRT bundle	Same size as
Small	`Qwen3.8-27B-BaseQuant-V1-Small.gguf` (10.93 GB)	`Qwen3.8-27B-BaseQuant-V1-Small.base`	unsloth `UD-IQ3_XXS` (10.93 GB)
Medium	`Qwen3.8-27B-BaseQuant-V1-Medium.gguf` (16.41 GB)	`Qwen3.8-27B-BaseQuant-V1-Medium.base`	unsloth `UD-Q4_K_M` (16.46 GB)
Large	`Qwen3.8-27B-BaseQuant-V1-Large.gguf` (20.82 GB)	`Qwen3.8-27B-BaseQuant-V1-Large.base`	unsloth `UD-Q5_K_XL` (20.88 GB)

Each GGUF is no larger than its unsloth counterpart. The Small bundle needs baseRT 0.4.0 or later.

Usage

# llama.cpp
llama-server -hf basecompute/Qwen3.8-27B-BaseQuant-V1 -hff Qwen3.8-27B-BaseQuant-V1-Medium.gguf -c 32768 -ngl 99


# SuperFluid
curl -fsSL https://superfluid.sh/install.sh | sh
superfluid serve basecompute/Qwen3.8-27B-BaseQuant-V1 --runtime llamacpp --pull-file Qwen3.8-27B-BaseQuant-V1-Medium.gguf

# baseRT
hf download basecompute/Qwen3.8-27B-BaseQuant-V1 Qwen3.8-27B-BaseQuant-V1-Large.base --local-dir .
basert serve ./Qwen3.8-27B-BaseQuant-V1-Large.base

Results

KL divergence of each quant's next-token distribution from the BF16 model, ours beside unsloth's quant of the same size, measured in llama.cpp. Lower is closer to BF16. The percentage over each pair is our change against unsloth.

Held-out text

On text that was not used to build these files, all three are 17–34% closer to BF16 than unsloth's quant of the same size.

Held-out text	Small vs UD-IQ3_XXS	Medium vs UD-Q4_K_M	Large vs UD-Q5_K_XL
Model's own continuations	0.0391 / 0.0308 (-21%)	0.00713 / 0.00555 (-22%)	0.00278 / 0.00200 (-28%)
Written text	0.5288 / 0.4318 (-18%)	0.2081 / 0.1579 (-24%)	0.1080 / 0.0716 (-34%)
Tool-call turns	0.0631 / 0.0526 (-17%)	0.0127 / 0.0099 (-22%)	0.00496 / 0.00354 (-29%)
Tool calls + final answers	0.0631 / 0.0523 (-17%)	0.0112 / 0.0090 (-20%)	0.00432 / 0.00320 (-26%)

Each cell: unsloth KL / BaseQuant KL (change). Bold marks the lower KL.

Public prompts

The prompts come from six public datasets (OpenHands, SWE-agent, Glaive function calling, OpenOrca, Tulu 3, OpenHermes). The BF16 model writes each continuation (thinking on), and both quants are scored along it.

Source	Small vs UD-IQ3_XXS	Medium vs UD-Q4_K_M	Large vs UD-Q5_K_XL
OpenHands	0.1190 / 0.0793 (-33%)	0.0212 / 0.0182 (-14%)	0.00450 / 0.00447 (-1%)
SWE-agent	0.0449 / 0.0330 (-27%)	0.00912 / 0.00708 (-22%)	0.00293 / 0.00241 (-18%)
Glaive function calling	0.0673 / 0.0628 (-7%)	0.0112 / 0.0098 (-13%)	0.00335 / 0.00325 (-3%)
OpenOrca	0.0515 / 0.0431 (-16%)	0.00759 / 0.00624 (-18%)	0.00248 / 0.00231 (-7%)
Tulu 3	0.0470 / 0.0402 (-14%)	0.00730 / 0.00585 (-20%)	0.00238 / 0.00231 (-3%)
OpenHermes	0.0445 / 0.0420 (-6%)	0.00639 / 0.00613 (-4%)	0.00203 / 0.00209 (+3%)
All six	0.0539 / 0.0460 (-15%)	0.00861 / 0.00731 (-15%)	0.00262 / 0.00253 (-3%)