Instructions to use arcee-ai/AFM-4.5B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use arcee-ai/AFM-4.5B-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("arcee-ai/AFM-4.5B-GGUF", dtype="auto")

llama-cpp-python

How to use arcee-ai/AFM-4.5B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="arcee-ai/AFM-4.5B-GGUF",
	filename="AFM-4.5B-IQ2_M.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use arcee-ai/AFM-4.5B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arcee-ai/AFM-4.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf arcee-ai/AFM-4.5B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf arcee-ai/AFM-4.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf arcee-ai/AFM-4.5B-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 arcee-ai/AFM-4.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf arcee-ai/AFM-4.5B-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 arcee-ai/AFM-4.5B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf arcee-ai/AFM-4.5B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/arcee-ai/AFM-4.5B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use arcee-ai/AFM-4.5B-GGUF with Ollama:
```
ollama run hf.co/arcee-ai/AFM-4.5B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use arcee-ai/AFM-4.5B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for arcee-ai/AFM-4.5B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for arcee-ai/AFM-4.5B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for arcee-ai/AFM-4.5B-GGUF to start chatting

Docker Model Runner
How to use arcee-ai/AFM-4.5B-GGUF with Docker Model Runner:
```
docker model run hf.co/arcee-ai/AFM-4.5B-GGUF:Q4_K_M
```

Lemonade

How to use arcee-ai/AFM-4.5B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull arcee-ai/AFM-4.5B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.AFM-4.5B-GGUF-Q4_K_M

List all available models

lemonade list

AFM-4.5B-GGUF

AFM-4.5B is a 4.5 billion parameter instruction-tuned model developed by Arcee.ai, designed for enterprise-grade performance across diverse deployment environments from cloud to edge. The base model was trained on a dataset of 8 trillion tokens, comprising 6.5 trillion tokens of general pretraining data followed by 1.5 trillion tokens of midtraining data with enhanced focus on mathematical reasoning and code generation. Following pretraining, the model underwent supervised fine-tuning on high-quality instruction datasets. The instruction-tuned model was further refined through reinforcement learning on verifiable rewards as well as for human preference. We use a modified version of TorchTitan for pretraining, Axolotl for supervised fine-tuning, and a modified version of Verifiers for reinforcement learning.

The development of AFM-4.5B prioritized data quality as a fundamental requirement for achieving robust model performance. We collaborated with DatologyAI, a company specializing in large-scale data curation. DatologyAI's curation pipeline integrates a suite of proprietary algorithms—model-based quality filtering, embedding-based curation, target distribution-matching, source mixing, and synthetic data. Their expertise enabled the creation of a curated dataset tailored to support strong real-world performance.

The model architecture follows a standard transformer decoder-only design based on Vaswani et al., incorporating several key modifications for enhanced performance and efficiency. Notable architectural features include grouped query attention for improved inference efficiency and ReLU^2 activation functions instead of SwiGLU to enable sparsification while maintaining or exceeding performance benchmarks.

The model available in this repo is the instruct model following supervised fine-tuning and reinforcement learning.

Model Details

Model Architecture: ArceeForCausalLM
Parameters: 4.5B
Training Tokens: 8T
License: Apache 2.0
Recommended settings:
- temperature: 0.5
- top_k: 50
- top_p: 0.95
- repeat_penalty: 1.1

Benchmarks

*Qwen3 and SmolLM's reasoning approach causes their scores to vary wildly from suite to suite - but these are all scores on our internal harness with the same hyperparameters. Be sure to reference their reported scores. SmolLM just released its bench.