Model Detail
Hermes-3-Llama-3.1-8B
—Hermes-3-Llama-3.1-8B is a large language model with 8B parameters released by Nous. The model is registered under the text-generation pipeline tag on Hugging Face, released under the llama3 license.
Open-LLM-Leaderboard scoring places it at MMLU-Pro 24, GPQA 6, IFEval 62, BBH 31, giving a sense of how it handles instruction following, reasoning, and graduate-level QA in absolute terms.
Hermes-3-Llama-3.1-8B ships as a LlamaForCausalLM / 💬 chat models (RLHF, DPO, IFT, ...) architecture with 8B parameters. Total weight footprint is approximately 8.0 GB, which is the relevant figure when planning local-inference VRAM. Distribution is governed by the llama3 license — review the exact terms before commercial deployment.
Hermes-3-Llama-3.1-8B is best fit for general-purpose chat and instruction-following workloads. 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.
Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling
arXiv:2609.38332v1 Announce Type: cross Abstract: Test-time scaling improves model performance by allocating additional compute during inference. Using this compute effectively across multiple context windows requires deciding how to allocate fresh contexts and what information to carry between them
HERMES: A Holistic End-to-End Risk-Aware Multimodal Embodied System with Vision-Language Models for Long-Tail Autonomous Driving
arXiv:2602.00993v3 Announce Type: replace-cross Abstract: End-to-end autonomous driving models increasingly benefit from large vision-language models for semantic understanding, yet safe and reliable planning under long-tail conditions remains challenging, particularly in mixed-traffic environments
HERMES: Contrast-Aware Knowledge Graph Reasoning from Clinical Notes for Patient Outcome Prediction
arXiv:2609.20825v1 Announce Type: new Abstract: Clinical predictive models often rely on structured Electronic Health Record data, such as time-series and procedure codes. While recent approaches have begun leveraging unstructured clinical notes, they typically encode them as flat sequences, which m
HERMES: Heterogeneous Edge-Relational Multi-Head Embedded SSM Attention for Traffic Conflict Prediction at Signalized Intersections
arXiv:2607.20505v1 Announce Type: cross Abstract: Surrogate safety measures (SSMs) enable proactive traffic safety assessment, but many existing methods evaluate pairwise interactions independently or flatten multi-agent scenes into fixed feature vectors, limiting their ability to represent heteroge
Hermes agent maker Nous Research in talks for new funding at $1.5B valuation
The company is raising at least $75 million, led by Robot Ventures, with significant participation from USV and other prominent investors.
