Arcee AI AFM-4.5B
4.5B-parameter foundation model trained on 6.58T curated tokens, achieving 200+ CPU tokens/sec with Western compliance standards, outperforming Qwen3-4B and Gemma3-4B across benchmarks.
About model
Arcee AI AFM-4.5B is a 4.5 billion parameter instruction-tuned model for enterprise-grade performance, excelling in mathematical reasoning and code generation. It is designed for diverse deployment environments and suitable for users requiring robust model performance.
API usage
Endpoint:
Model card
AFM-4.5B is Arcee AI's first foundation model, trained on 6.58T curated tokens via partnership with DatologyAI. Optimized for enterprise deployment with Western compliance standards and efficient CPU/GPU inference.
Key Improvements:
- 200+ tokens/sec CPU performance on 4-bit quantization
- Enterprise-grade compliance for regulated industries
- Multi-stage post-training with RL and KTO alignment
- Model providerArcee AI
- TypeLLM
- Main use casesChat
- DeploymentServerlessOn-Demand Dedicated
- Endpoint
- Parameters4.6B
- Context length65k
- Input price
$0.10 / 1M tokens
- Output price
$0.40 / 1M tokens
- Input modalitiesText
- Output modalitiesText
- ReleasedJuly 29, 2025
- External link
- CategoryChat