Model reference · open weights
Ovis2 is an open-weight language model from ATH-MaaS. Ovis2-1B (BF16) weighs 2.5 GB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the ATH-MaaS/Ovis2-1B model card, 2026-10-01
What it is
| Released by | ATH-MaaS |
|---|---|
| Released | 2025-02-10 |
| Parameters | 1.3B |
| VRAM | 2.5 GB for the weights |
What it runs on
| Card | Requests at once | Context max | Memory | |
|---|---|---|---|---|
| 8K each | 32K each | |||
| RTX 3060 12 GB | 83 | 20 | all 32K | 11.6 GB |
| RTX 4060 Ti 16 GB | 121 | 30 | all 32K | 15.4 GB |
| RTX 3090 24 GB | 200 | 50 | all 32K | 23.4 GB |
| RTX 4090 24 GB | 200 | 50 | all 32K | 23.4 GB |
| RTX 5090 32 GB | 276 | 69 | all 32K | 31.0 GB |
| L40S 48 GB | 405 | 101 | all 32K | 44.0 GB |
| A100 80 GB | 745 | 186 | all 32K | 78.2 GB |
| H100 80 GB | 704 | 176 | all 32K | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | 860 | 215 | all 32K | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | 995 | 248 | all 32K | 107 GB |
| H200 141 GB | 1000+ | 324 | all 32K | 138 GB |
| B200 180 GB | 1000+ | 419 | all 32K | 176 GB |
| Requests at once | 8K tokens each | 32K tokens each |
|---|---|---|
| 1 | 3.3 GB | 3.6 GB |
| 5 | 3.7 GB | 5.2 GB |
| 8 | 4.0 GB | 6.4 GB |
| 16 | 4.8 GB | 9.6 GB |
| 32 | 6.4 GB | 16.1 GB |
| 64 | 9.6 GB | 28.9 GB |
One card, with vLLM's small-card settings.
Builds
From the model card
We are pleased to announce the release of Ovis2, our latest advancement in multi-modal large language models (MLLMs). Ovis2 inherits the innovative architectural design of the Ovis series, aimed at structurally aligning visual and textual embeddings. As the successor to Ovis1.6, Ovis2 incorporates significant improvements in both dataset curation and training methodologies.
Key Features:
Small Model Performance: Optimized training strategies enable small-scale models to achieve higher capability density, demonstrating cross-tier leading advantages.
Enhanced Reasoning Capabilities: Significantly strengthens Chain-of-Thought (CoT) reasoning abilities through the combination of instruction tuning and preference learning.
Video and Multi-Image Processing: Video and multi-image data are incorporated into training to enhance the ability to handle complex visual information across frames and images.
Multilingual Support and OCR: Enhances multilingual OCR beyond English and Chinese and improves structured data extraction from complex visual elements like tables and charts.
| Ovis MLLMs | ViT | LLM | Model Weights | Demo |
|---|---|---|---|---|
| Ovis2-1B | aimv2-large-patch14-448 | Qwen2.5-0.5B-Instruct | Huggingface | Space |
| Ovis2-2B | aimv2-large-patch14-448 | Qwen2.5-1.5B-Instruct | Huggingface | Space |
| Ovis2-4B | aimv2-huge-patch14-448 | Qwen2.5-3B-Instruct | Huggingface | Space |
| Ovis2-8B | aimv2-huge-patch14-448 | Qwen2.5-7B-Instruct | Huggingface | Space |
| Ovis2-16B | aimv2-huge-patch14-448 | Qwen2.5-14B-Instruct | Huggingface | Space |
| Ovis2-34B | aimv2-1B-patch14-448 | Qwen2.5-32B-Instruct | Huggingface | - |
We use VLMEvalKit, as employed in the OpenCompass multimodal and reasoning leaderboard, to evaluate Ovis2.
| Benchmark | Qwen2.5-VL-3B | SAIL-VL-2B | InternVL2.5-2B-MPO | Ovis1.6-3B | InternVL2.5-1B-MPO | Ovis2-1B | Ovis2-2B |
|---|---|---|---|---|---|---|---|
| MMBench-V1.1test | 77.1 | 73.6 | 70.7 | 74.1 | 65.8 | 68.4 | 76.9 |
| MMStar | 56.5 | 56.5 | 54.9 | 52.0 | 49.5 | 52.1 | 56.7 |
| MMMUval | 51.4 | 44.1 | 44.6 | 46.7 | 40.3 | 36.1 | 45.6 |
| MathVistatestmini | 60.1 | 62.8 | 53.4 | 58.9 | 47.7 | 59.4 | 64.1 |
| HallusionBench | 48.7 | 45.9 | 40.7 | 43.8 | 34.8 | 45.2 | 50.2 |
| AI2D | 81.4 | 77.4 | 75.1 | 77.8 | 68.5 | 76.4 | 82.7 |
| OCRBench | 83.1 | 83.1 | 83.8 | 80.1 | 84.3 | 89.0 | 87.3 |
| MMVet | 63.2 | 44.2 | 64.2 | 57.6 | 47.2 | 50.0 | 58.3 |
| MMBenchtest | 78.6 | 77 | 72.8 | 76.6 | 67.9 | 70.2 | 78.9 |
| MMT-Benchval | 60.8 | 57.1 | 54.4 | 59.2 | 50.8 | 55.5 | 61.7 |
| RealWorldQA | 66.5 | 62 | 61.3 | 66.7 | 57 | 63.9 | 66.0 |
| BLINK | 48.4 | 46.4 | 43.8 | 43.8 | 41 | 44.0 | 47.9 |
| QBench | 74.4 | 72.8 | 69.8 | 75.8 | 63.3 | 71.3 | 76.2 |
| ABench | 75.5 | 74.5 | 71.1 | 75.2 | 67.5 | 71.3 | 76.6 |
| MTVQA | 24.9 | 20.2 | 22.6 | 21.1 | 21.7 | 23.7 | 25.6 |
| Benchmark | Qwen2.5-VL-3B | InternVL2.5-2B | InternVL2.5-1B | Ovis2-1B | Ovis2-2B |
|---|---|---|---|---|---|
| VideoMME(wo/w-subs) | 61.5/67.6 | 51.9 / 54.1 | 50.3 / 52.3 | 48.6/49.5 | 57.2/60.8 |
| MVBench | 67.0 | 68.8 | 64.3 | 60.32 | 64.9 |
| MLVU(M-Avg/G-A |
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.