Author's Description
AFM-4.5B is a 4.5 billion parameter instruction-tuned language model developed by Arcee AI. The model was pretrained on approximately 8 trillion tokens, including 6.5 trillion tokens of general data and 1.5 trillion tokens with an emphasis on mathematical reasoning and code generation.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Arcee AI's AFM-4.5B model demonstrates moderate speed performance, ranking in the 38th percentile across benchmarks. It offers cost-effective solutions, typically falling within the 68th percentile for price. Notably, the model exhibits exceptional reliability with a 99% success rate, indicating consistent and usable responses. In terms of performance across categories, AFM-4.5B shows a solid ability to acknowledge uncertainty, achieving 92.0% accuracy in hallucination detection. Its general knowledge is also strong at 95.0% accuracy. However, the model struggles significantly in more complex cognitive tasks. It shows weaknesses in Ethics (91.0% accuracy, 25th percentile), Mathematics (51.0% accuracy, 24th percentile), Instruction Following (22.7% accuracy, 26th percentile), and particularly in Reasoning (25.5% accuracy, 17th percentile). While its Coding performance is moderate at 66.3% accuracy, its Email Classification accuracy is low at 88.0% (12th percentile). Key strengths include its high reliability, cost-effectiveness, and proficiency in general knowledge and identifying fictional concepts. Its notable weaknesses lie in advanced reasoning, mathematical problem-solving, and precise instruction following, suggesting areas for further development.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.048 |
| Completion | $0.15 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Together
|
Together | arcee-ai/afm-4.5b | 65K | $0.048 / 1M tokens | $0.15 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by arcee-ai
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| Arcee AI: Trinity Mini | Dec 01, 2025 | ~26B | 131K |
Text input
Text output
|
★ | ★★ | $$$ |
| Arcee AI: Caller Large Unavailable | May 05, 2025 | — | 32K |
Text input
Text output
|
★★★★★ | ★★★ | $$$$ |
| Arcee AI: Spotlight | May 05, 2025 | ~7B | 131K |
Image input
Text input
Text output
|
★★★★★ | ★★★ | $$ |
| Arcee AI: Maestro Reasoning | May 05, 2025 | ~32B | 131K |
Text input
Text output
|
★★ | ★★★★ | $$$$$ |
| Arcee AI: Virtuoso Large | May 05, 2025 | ~72B | 131K |
Text input
Text output
|
★★★★★ | ★★★★ | $$$$ |
| Arcee AI: Coder Large | May 05, 2025 | ~32B | 32K |
Text input
Text output
|
★★★★★ | ★★★★ | $$$ |
| Arcee AI: Virtuoso Medium V2 Unavailable | May 05, 2025 | ~32B | 131K |
Text input
Text output
|
★★★★★ | ★★★★ | $$$ |
| Arcee AI: Arcee Blitz Unavailable | May 05, 2025 | ~24B | 32K |
Text input
Text output
|
★★★★ | ★★★★ | $$$ |