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

Use Docker

docker model run hf.co/loqy/Nanbeige4.2-3B-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use loqy/Nanbeige4.2-3B-GGUF with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/loqy/Nanbeige4.2-3B-GGUF:Q4_K_M

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

How to use loqy/Nanbeige4.2-3B-GGUF with Pi:

Start the llama.cpp server

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

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use loqy/Nanbeige4.2-3B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull loqy/Nanbeige4.2-3B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Nanbeige4.2-3B-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use loqy/Nanbeige4.2-3B-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 loqy/Nanbeige4.2-3B-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 loqy/Nanbeige4.2-3B-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use loqy/Nanbeige4.2-3B-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf loqy/Nanbeige4.2-3B-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 "loqy/Nanbeige4.2-3B-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 GGUF, tokenizer-faithful

A Q4_K_M conversion of Nanbeige/Nanbeige4.2-3B that keeps the model's BPE merge table, so it tokenizes the way the model was trained.

Why this exists

Every published GGUF conversion of this model that we measured drops the merge table. The model's tokenizer is BPE with 296,888 merges over a Metaspace pre-tokenizer; the stock conversion path exports it as SentencePiece with tokenizer.ggml.model = llama, no merges, and synthesized scores equal to the negation of each token's rank. A unigram Viterbi over those scores approximates BPE and agrees with it on common text, but not everywhere.

Measured over 6,857 strings (English and French prose, source code, JSON and tool-call payloads, Chinese, adversarial whitespace, and vocabulary-boundary concatenations):

Conversion	Divergent from the reference tokenizer
`owao/Nanbeige4.2-3B-GGUF`	34.5%
`bartowski/Nanbeige_Nanbeige4.2-3B-GGUF`	same tokenizer shape
`Andgihat/Nanbeige4.2-3B-GGUF`	same tokenizer shape
this repository	0.00%

Example, taken from ordinary prose:

"  silently implementing them."
  SPM conversion  [259, 75410, 14250, 876, 152361]        (5 tokens)
  reference       [259, 24049, 1787, 14250, 876, …]       (6 tokens)

Provenance

Item	Value
Source weights	`Nanbeige/Nanbeige4.2-3B` revision `451ed48c3273ecef7ea8faaa43c31ce529763bb1`
Converter	`llama.cpp` `b10731` (`0eadefebd3f8f92a86d634a0e5b8fffc9dc792c0`) with `conversion/nanbeige.py` replaced by the file in this repository
Quantizer	`llama-quantize` from the same `b10731` release, `Q4_K_M`
File	`Nanbeige4.2-3B-Q4_K_M.gguf`, 2,579,880,160 bytes
SHA-256	`01739fad13be318c5c8620f8de52731608bb750ae887e9445cc81cb4a189e45d`
License	Apache-2.0, unchanged from upstream

conversion-nanbeige.py in this repository is the exact converter used. It follows Gemma4Model.set_vocab: export the BPE vocabulary, declare tokenizer.ggml.model and .pre as gemma4 (which selects LLAMA_VOCAB_TYPE_BPE and the SPM-style Metaspace pre-tokenizer already in llama.cpp), and load the merge table.

Known limitation

llama.cpp's BPE path escapes whitespace inside each fragment but never prepends the leading U+2581 that this model's Metaspace pre-tokenizer (prepend_scheme: "first") requires, and it does not read tokenizer.ggml.add_space_prefix — only the SPM and UGM tokenizers consult it.

In practice the first token of a prompt loses its leading ▁ (system instead of ▁system). That is one token per request, with no divergence anywhere else. Supplying the leading space yourself reproduces the reference exactly, which is how the 0.00% above was measured.

The clean fix belongs upstream, in the BPE tokenizer rather than in any GGUF.

Recommended sampling

From the model card: temperature 0.6, top-p 0.95, top-k 20 for reasoning and chat; the publisher recommends temperature 1.0 for agentic and tool-use work.

Trademarks

Nanbeige is a trademark of its owner. This repository redistributes an Apache-2.0 model under its original terms and claims no affiliation or endorsement.

Downloads last month: -

GGUF

Model size

4B params

Architecture

nanbeige

Hardware compatibility

4-bit

Model tree for loqy/Nanbeige4.2-3B-GGUF

Base model

Nanbeige/Nanbeige4.2-3B-Base

Finetuned

Nanbeige/Nanbeige4.2-3B

Quantized

(47)

this model