Instructions to use precision-numerics/Boole-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use precision-numerics/Boole-1.7B 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 precision-numerics/Boole-1.7B:Q1_0
# Run inference directly in the terminal:
llama cli -hf precision-numerics/Boole-1.7B:Q1_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf precision-numerics/Boole-1.7B:Q1_0
# Run inference directly in the terminal:
llama cli -hf precision-numerics/Boole-1.7B:Q1_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 precision-numerics/Boole-1.7B:Q1_0
# Run inference directly in the terminal:
./llama-cli -hf precision-numerics/Boole-1.7B:Q1_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 precision-numerics/Boole-1.7B:Q1_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf precision-numerics/Boole-1.7B:Q1_0

Use Docker

docker model run hf.co/precision-numerics/Boole-1.7B:Q1_0

LM Studio
Jan

vLLM

How to use precision-numerics/Boole-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "precision-numerics/Boole-1.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "precision-numerics/Boole-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/precision-numerics/Boole-1.7B:Q1_0

Ollama
How to use precision-numerics/Boole-1.7B with Ollama:
```
ollama run hf.co/precision-numerics/Boole-1.7B:Q1_0
```
Unsloth Desktop

How to use precision-numerics/Boole-1.7B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf precision-numerics/Boole-1.7B:Q1_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": "precision-numerics/Boole-1.7B:Q1_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use precision-numerics/Boole-1.7B with Docker Model Runner:
```
docker model run hf.co/precision-numerics/Boole-1.7B:Q1_0
```

Lemonade

How to use precision-numerics/Boole-1.7B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull precision-numerics/Boole-1.7B:Q1_0

Run and chat with the model

lemonade run user.Boole-1.7B-Q1_0

List all available models

lemonade list

Hermes Agent

How to use precision-numerics/Boole-1.7B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf precision-numerics/Boole-1.7B:Q1_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 precision-numerics/Boole-1.7B:Q1_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use precision-numerics/Boole-1.7B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf precision-numerics/Boole-1.7B:Q1_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 "precision-numerics/Boole-1.7B:Q1_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"

Boole-1.7B

A small and strong 1-bit LLM

💬 On-Device Chat · Blog · Code

Boole-1.7B is a 1-bit language model derived from Qwen3-1.7B. Its weights take 247 MB, 13.9× less than the BF16 original, and it keeps 85.9% of the original's ten-task benchmark average (50.55 vs 58.83).

Files

File	Runtime	Size
Boole-1.7B.safetensors	vLLM + Humming · CUDA	247.1 MB
Boole-1.7B-Q1_0.gguf	llama.cpp · CPU or CUDA	292.1 MB

The GGUF is larger because it stores the embedding and output matrices separately.

Quick start

Use the boole-demo repository, which builds the pinned llama.cpp and contains the vLLM + Humming loader.

git clone https://github.com/PrecisionNumerics/boole-demo.git && cd boole-demo
hf download precision-numerics/Boole-1.7B Boole-1.7B-Q1_0.gguf --local-dir model
bash scripts/setup_llama_cpp.sh            # GGML_CUDA=0 for CPU only
third_party/llama.cpp/build/bin/llama-server \
    -m model/Boole-1.7B-Q1_0.gguf -ngl 99 -c 4096 \
    --chat-template-kwargs '{"enable_thinking": false}'

Use -ngl 0 on CPU, then open the server URL. For vLLM + Humming (CUDA, vLLM 0.31.0 and humming-kernels 0.1.16), follow the repository README.

Intended use

English-language inference in non-thinking mode (enable_thinking=false).

Evaluation

Scores are the equal-weight mean of ten tasks: MMLU-Redux, GPQA-Diamond, MuSR, IFEval, IFBench, GSM8K, MATH-500, HumanEval+, MBPP+ and BFCLv3, run in non-thinking mode with greedy decoding (GPQA-Diamond averages ten sampled runs). Harness: EvalScope 1.4.2 and bfcl-eval 2025.10.27.1. See the blog for the comparison.

Full evaluation settings

We use the same evaluation settings as PrismML's Bonsai. The settings below cover 10 generative benchmarks.

Setting	Value
Few-shot examples	0
Generative prompts	Benchmark prompts with the checkpoint's chat template
Thinking mode	Disabled (`enable_thinking=false`)
Default generation	Greedy: temperature 0, top-p 1
Default seed / repetitions	Seed 42; one response per example
Additional sampling filters	Top-k and min-p disabled; repetition penalty 1.0
Dataset limit	Full benchmark splits; no sample limit

GPQA-Diamond uses temperature 0.6, top-p 0.95, and 10 repetitions per example with seeds 42–51. Its score is averaged across those repetitions.

Maximum generated tokens per response:

Benchmark	Max new tokens
MMLU-Redux	2,048
GPQA-Diamond	8,192
MuSR	2,048
IFEval	4,096
IFBench	4,096
GSM8K	2,048
MATH-500	8,192
HumanEval+	8,192
MBPP+	4,096
BFCL-v3	4,096

Generation context is 16,384 tokens by default and 40,960 for BFCL-v3, capped when a checkpoint specifies a lower limit. Concurrency and memory allocation are tuned to the runtime and available GPU memory.

IFEval and IFBench report the mean of strict prompt-level and instruction-level accuracy. HumanEval+ and MBPP+ use augmented tests and pass@1. BFCL-v3 reports the macro average of 13 single-turn subsets, with is_fc_model=false and underscore_to_dot=false. GSM8K and MATH-500 use a 10-second per-answer scoring deadline; timed-out answers receive zero.

Evaluation packages: EvalScope 1.4.2 and bfcl-eval 2025.10.27.1.

License

Weights and runtime code use Apache 2.0. NOTICE includes upstream Qwen attribution.

Citation

@misc{precisionnumerics2026boole1p7b,
  author = {{Precision Numerics}},
  title = {{Boole}-1.7B},
  year = {2026},
  month = {October},
  url = {https://huggingface.co/precision-numerics/Boole-1.7B}
}

Downloads last month: 25

GGUF

Model size

2B params

Architecture

qwen3

Hardware compatibility

1-bit

Model tree for precision-numerics/Boole-1.7B

Base model

Qwen/Qwen3-1.7B-Base

Finetuned

Qwen/Qwen3-1.7B

Quantized

(416)

this model