Instructions to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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": "Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M

Ollama
How to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF with Ollama:
```
ollama run hf.co/Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M
```
Unsloth Desktop

How to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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": "Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF with Docker Model Runner:
```
docker model run hf.co/Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M
```

Lemonade

How to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nanbeige4.2-3B-CE-v1.0-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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 "Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-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"

Nanbeige4.2-3B-CE v1.0 — GGUF

GGUF builds of Nanbeige4.2-3B-CE v1.0, a Computer Engineering and systems-focused fine-tune of Nanbeige/Nanbeige4.2-3B.

Canonical merged BF16 release:

Irfanuruchi/Nanbeige4.2-3B-CE-v1.0

Available GGUF files

File	Quantization	Approx. model size
`Nanbeige4.2-3B-CE-v1.0-BF16.gguf`	BF16 reference	7953.53 MiB
`Nanbeige4.2-3B-CE-v1.0-Q8_0.gguf`	Q8_0	4225.56 MiB
`Nanbeige4.2-3B-CE-v1.0-Q6_K.gguf`	Q6_K	3262.50 MiB
`Nanbeige4.2-3B-CE-v1.0-Q4_K_M.gguf`	Q4_K_M	2451.74 MiB

Q4_K_M is the recommended compact general-use build.

Q6_K provides a higher-quality size/performance balance.

Q8_0 is a high-fidelity quantized build.

BF16 is the GGUF reference representation.

Conversion

Converted from the frozen local merged BF16 v1.0 release using llama.cpp commit:

73a43d1f69345aee8bb186ef4b3172cef892f2e5

The converter recognized the model as native GGUF architecture:

nanbeige

Important architecture metadata preserved:

22 blocks
3072 embedding dimension
10752 feed-forward dimension
48 attention heads
8 KV heads
262144 configured context length
num_loops = 2
skip_loop_final_norm = false

All released GGUF files were successfully generated with llama.cpp and locally runtime-smoke-tested.

SHA-256

See SHA256SUMS for the exact hashes of every GGUF artifact.

Usage

Example with llama.cpp:

llama-cli \
  -m Nanbeige4.2-3B-CE-v1.0-Q4_K_M.gguf

The model contains its tokenizer and chat template in GGUF metadata.

Validation and limitations

These GGUF builds are format/runtime conversions of the frozen v1.0 model. Quantization does not constitute a new training checkpoint or a new factual-quality release gate.

Nanbeige4.2-3B-CE v1.0 is the best validated release checkpoint selected during development, but it is not claimed to be perfect. Some known precision/factual weaknesses remain in difficult systems questions.

Refer to the canonical BF16 model card for the primary validation notes and limitations.

License

Apache-2.0. See LICENSE.

Base model: Nanbeige/Nanbeige4.2-3B.

Downloads last month: 183

GGUF

Model size

4B params

Architecture

nanbeige

Hardware compatibility

4-bit

6-bit

8-bit

16-bit

Model tree for Irfanuruchi/Nanbeige4.2-3B-CE-v1.0-GGUF

Base model

Nanbeige/Nanbeige4.2-3B-Base

Finetuned

Nanbeige/Nanbeige4.2-3B

Finetuned

Irfanuruchi/Nanbeige4.2-3B-CE-v1.0

Quantized

(4)

this model