Instructions to use schneewolflabs/B0-9B-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 schneewolflabs/B0-9B-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 schneewolflabs/B0-9B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf schneewolflabs/B0-9B-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf schneewolflabs/B0-9B-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf schneewolflabs/B0-9B-GGUF:Q8_0

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 schneewolflabs/B0-9B-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf schneewolflabs/B0-9B-GGUF:Q8_0

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 schneewolflabs/B0-9B-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf schneewolflabs/B0-9B-GGUF:Q8_0

Use Docker

docker model run hf.co/schneewolflabs/B0-9B-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use schneewolflabs/B0-9B-GGUF with Ollama:
```
ollama run hf.co/schneewolflabs/B0-9B-GGUF:Q8_0
```
Unsloth Desktop

How to use schneewolflabs/B0-9B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf schneewolflabs/B0-9B-GGUF:Q8_0

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": "schneewolflabs/B0-9B-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use schneewolflabs/B0-9B-GGUF with Docker Model Runner:
```
docker model run hf.co/schneewolflabs/B0-9B-GGUF:Q8_0
```

Lemonade

How to use schneewolflabs/B0-9B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull schneewolflabs/B0-9B-GGUF:Q8_0

Run and chat with the model

lemonade run user.B0-9B-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use schneewolflabs/B0-9B-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 schneewolflabs/B0-9B-GGUF:Q8_0

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 schneewolflabs/B0-9B-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use schneewolflabs/B0-9B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf schneewolflabs/B0-9B-GGUF:Q8_0

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 "schneewolflabs/B0-9B-GGUF:Q8_0" \
  --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"

B0-9B — GGUF

Q8_0 (the quant every benchmark number was measured on) and vision mmproj for schneewolflabs/B0-9B.

llama-server -m B0-9B-Q8_0.gguf -ngl 99 -c 8192 --jinja -fa on -np 1 \
    --spec-type draft-mtp --spec-draft-n-max 4 \
    --mmproj B0-9B-mmproj-f16.gguf

Deployment guide (measured)

mradermacher's static and imatrix quants of this model were benchmarked on the 47-case operator tool bench (Q8_0 anchor: 46/47). Highlights:

quant	size	tool bench	note
Q8_0	9.8GB	46/47	reference
Q6_K / Q5_K_M	8.0 / 6.9GB	45/47
i1-Q3_K_M	4.7GB	45/47	the sweet spot — near-Q8 at half the size (verified ×2)
IQ4_XS	5.3GB	43/47	best static 4-bit
Q4_K_M / Q4_K_S	5.9 / 5.6GB	42/47
i1-Q2_K	3.9GB	39/47	smallest usable — imatrix rescues 2-bit
Q5_K_S	6.8GB	38/47 ⚠	defective (verified ×2) — use Q5_K_M
Q2_K (static)	3.9GB	~3/47 ✗	tool calling collapses entirely

Rules that came out of the measurement matrix (i1-Q3_K_M, RTX A6000; ratios transfer):

Always --jinja and -fa on. Tool calling depends on the chat template.
Offload every layer you can. Quality is unaffected by partial offload, but each CPU layer costs ~20% generation speed at the top of the curve (34 layers: 102 tok/s → 33: 82 → 32: 67 → 30: 50). Prefill degrades much more gently.
Keep the KV cache at f16. This is a hybrid-attention architecture — KV costs only ~33MB per 1k tokens — and every cache quantization measured (q8/q8, q8/q4, q4/q4) cost 1–2 tool-bench cases while saving little. Quantize cache only when a context target won't otherwise fit.
The imatrix.gguf in the i1 repo is for re-quantizing, not inference — the i1 GGUFs are self-contained.

6GB VRAM recipes (i1-Q3_K_M, 139MB/layer):

# 32k context, full quality, full speed — ~5.6GB
llama-server -m B0-9B.i1-Q3_K_M.gguf -ngl 99 -c 32768 --jinja -fa on -np 1

# 64k context — ~5.7GB, costs ~2 tool-bench cases
llama-server -m B0-9B.i1-Q3_K_M.gguf -ngl 99 -c 65536 --jinja -fa on -np 1 \
    --cache-type-k q8_0 --cache-type-v q8_0

# <5.5GB usable (display attached): the resurrected 2-bit
llama-server -m B0-9B.i1-Q2_K.gguf -ngl 99 -c 32768 --jinja -fa on -np 1

Vision (--mmproj) adds ~1GB — skip it on 6GB cards.

Downloads last month: 184

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for schneewolflabs/B0-9B-GGUF

Base model

hemlang/Hemlock-Qwen3.5-9B

Finetuned

schneewolflabs/Wichtelchen-Qwen3.5-9B

Finetuned

schneewolflabs/B0-9B

Quantized

(3)

this model