Model Detail
Orthrus-Qwen3-8B
—Orthrus-Qwen3-8B is a code generation model with 8B parameters released by chiennv. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under the permissive cc-by-4.0 license.
Orthrus-Qwen3-8B ships with 8B parameters. Total weight footprint is approximately 9.7 GB, which is the relevant figure when planning local-inference VRAM. The cc-by-4.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Orthrus-Qwen3-8B is best fit for code completion, repository-scale Q&A, and pair-programming integrations. 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.
How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in Orthrus
arXiv:2609.15504v1 Announce Type: cross Abstract: Orthrus is a hybrid autoregressive-diffusion architecture that accelerates autoregressive language-model inference by generating multiple tokens in parallel while using a frozen autoregressive backbone. Its central claim is that an intra-model consen
Orthrus: Memory-Efficient Parallel Token Generation via Dual-View Diffusion
arXiv:2605.12825v2 Announce Type: replace-cross Abstract: We introduce Orthrus, a simple and efficient dual-architecture framework that unifies the exact generation fidelity of autoregressive Large Language Models (LLMs) with the high-speed parallel token generation of diffusion models. The sequenti
