Model Detail
reka-edge-2603
—reka-edge-2603 is a code generation model with 3.6B parameters released by RekaAI. The model is registered under the image-text-to-text pipeline tag on Hugging Face, and supports text+image+video->text inputs, distributed under a other license.
reka-edge-2603 is priced at $0.1/M input tokens and $0.1/M output tokens. Operationally the model offers a 16K-token context window, which matters when sizing it for prompt-heavy or latency-sensitive workloads. At this input rate the model sits in the commodity tier and is suitable for high-volume workloads where per-call cost dominates the decision.
reka-edge-2603 ships with 3.6B parameters. Total weight footprint is approximately 7.1 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the other license — review the exact terms before commercial deployment.
reka-edge-2603 is best fit for code completion, repository-scale Q&A, and pair-programming integrations, and high-volume batch jobs where per-call cost dominates the budget. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery
arXiv:2606.13662v2 Announce Type: replace Abstract: LLM-based agents have shown increasing potential in automating scientific discovery. Given an optimizable metric and an execution environment, they can propose, validate, and iterate scientific solutions, and have produced results that outperform h
Eureka: Intelligent Feature Engineering for Enterprise AI Cloud Resource Demand Prediction
arXiv:2605.25297v2 Announce Type: replace-cross Abstract: Effective features are crucial for predictive model performance, but creating them often requires domain expertise, limiting scalability across applications. We define feature engineering as an agentic code generation problem: features are no
