Model reference · open weights

OneRec

Available as managed deployment LLMs OpenOneRec · community Text gen 2 variants 105k dl/mo

OneRec is an open-weight language model from OpenOneRec. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byOpenOneRec
TypeLanguage models
TaskText gen
Parameters (lead)2.1B
Context40k tokens
Runs withtransformers
Released2025-12-30
Popularity105k downloads / month
LicenceOpen weights

About

What OneRec is

📖 Introduction

OpenOneRec is an open-source framework designed to bridge the gap between traditional recommendation systems and Large Language Models (LLMs). While Generative Recommendation has shown promise, existing models often struggle with isolated data silos and a lack of reasoning capabilities.

To address this, we introduce a unified framework that comprises:

Read the full model card
  • RecIF-Bench: The first holistic Recommendation Instruction-Following Benchmark, containing 100M interactions from 200k users across heterogeneous domains (Short Video, Ads, Product).
  • OneRec-Foundation Models: A family of models (1.7B & 8B) built on the Qwen3 backbone. The series includes Standard versions trained on our open-source dataset and Pro versions enhanced with a hundred-billion-token industrial corpus from Kuaishou.
  • Full-Stack Pipeline: We open-source our comprehensive training pipeline, including data processing, co-pretraining, and post-training, to ensure full reproducibility and facilitate scaling law research in recommendation.

🔥 News

  • [2026.1.1] 📑 The technical report has been released.
  • [2026.1.1] 🎉 OneRec-Foundation models (1.7B, 8B) are now available on Hugging Face!
  • [2026.1.1] 🚀 RecIF-Bench dataset and evaluation scripts are open-sourced.
  • [2026.1.5] 🔡 OneRec-Tokenizer is open-sourced to support SID generation for new domains.

📊 RecIF-Bench

We propose RecIF-Bench to rigorously assess the synergy between instruction following and domain-specific recommendation. It organizes 8 distinct tasks into a four-layer capability hierarchy:

  • Layer 0: Semantic Alignment (Item Understanding)
  • Layer 1: Fundamental Prediction (Short Video Rec, Ad Rec, Product Rec, Label Prediction)
  • Layer 2: Instruction Following (Interactive Rec, Label-Conditional Rec)
  • Layer 3: Reasoning (Recommendation Explanation)

The benchmark aggregates data from three domains: Short Video (Content), Ads (Commercial), and Product (E-commerce).

🤖 Model Zoo

The OpenOneRec-Foundation series is built upon the Qwen architecture, enhanced with Itemic Tokens for modality alignment and trained via a multi-stage protocol.

ModelBackboneParametersDescriptionLink
OneRec-1.7BQwen3-1.7B1.7BStandard version trained on open-source data (~33B tokens)HuggingFace
OneRec-8BQwen3-8B8BStandard version trained on open-source data (~33B tokens)HuggingFace
OneRec-1.7B-ProQwen3-1.7B1.7BScaled-up version with expanded datasets (~130B tokens)HuggingFace
OneRec-8B-ProQwen3-8B8BScaled-up version with expanded datasets (~130B tokens)HuggingFace

🏗️ Method & Architecture

OpenOneRec reframes recommendation as a general-purpose sequence modeling paradigm.

1. Items as Tokens

To bridge the modality gap, we treat items as a distinct modality using Itemic Tokens derived from hierarchical vector quantization. This allows the LLM to process interaction history as a cohesive context sequence.

2. Training Pipeline

Our framework utilizes the following recipe:

  • Pre-Training: Integrates collaborative signals via Itemic-Text Alignment and Full-Parameter Co-Pretraining.
  • Post-Training:
    • Stage 1: Multi-task Supervised Fine-tuning for basic instruction following.
    • Stage 2: On-policy Distillation to restore general reasoning performance.
    • Stage 3: Reinforcement Learning to enhance recommendation capabilities.

📈 Performance

Results on RecIF-Bench

OpenOneRec-Foundation achieves State-of-the-Art (SOTA) results across RecIF-Bench tasks, significantly outperforming baselines like LC-Rec and TIGER.

TaskMetricSASRecTIGERLC-RecOneRec-1.7BOneRec-8BOneRec-1.7B-ProOneRec-8B-Pro
Short Video RecRecall@320.01190.01320.01800.02720.03550.02740.0369
Ad RecRecall@320.02930.05810.07230.07070.08770.07350.0964
Product RecRecall@320.01750.02830.04160.03600.04700.04050.0538
Label-Cond. RecRecall@320.01400.01230.01700.01840.02280.01820.0235
Label Pred.AUC0.62440.66750.61390.61840.66150.60710.6912
Interactive RecRecall@32----0.23940.19410.30320.20240.3458
Item Und.LLM Score----0.25170.31750.32020.31330.3209
Rec. ExplanationLLM Score----3.93503.35403.67743.50604.0381

Cross-Domain Transferability

On the Amazon Benchmark (10 datasets), OpenOneRec demonstrates exceptional zero-shot/few-shot transfer capabilities, achieving an average 26.8% improvement in Recall@10 over the second-best method.

DomainSASRecTIGERLC-RecOurs
Baby0.03810.03180.03440.0513
Beauty0.06390.06280.07640.0924
Cell Phones0.07820.07860.08830.1036
Grocery0.07890.06910.07900.1029
Health0.05060.05340.06160.0768
Home0.02120.02160.02930.0390
Pet Supplies0.06070.05420.06120.0834
Sports0.03890.03310.04180.0547
Tools0.04370.03440.04380.0593
Toys0.06580.05270.05490.0953

Metric: Recall@10. Ours refers to OneRec-Foundation with text-augmented itemic tokens strategy.

🚀 Quick Start

Code release and detailed usage instructions are coming soon.

Currently, you can load our models using `transformers>=4.51

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys onerec for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (onerec below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"onerec","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms