Ovis2.5 2B
Ovis2.5 2B is an open-weights language model from Qwen, released August 15, 2025. It has 2.6B parameters (dense). The context window is 40K tokens.
We present Ovis2.5, a successor to Ovis2 designed for native-resolution visual perception and strong multimodal reasoning. Ovis2.5 integrates a native-resolution vision transformer that processes images at their native, variable resolutions, avoiding the degradation from fixed-resolution tiling and preserving both …
Check it against your own PC →
Can you run Ovis2.5 2B locally?
The smallest common GPU it runs on is 6 GB of VRAM (with 32 GB of RAM): Q6_K, fully on GPU, roughly 52 tokens per second. Estimates assume 32 GB of DDR5 RAM, a 16K context and llama.cpp-style GGUF quantization. Enter your exact hardware in the live app.
| GPU memory | Verdict | Best quant | VRAM | RAM | tok/s |
|---|---|---|---|---|---|
| 6 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.6 GB | – | ~52 |
| 8 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.6 GB | – | ~72 |
| 12 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.6 GB | – | ~93 |
| 16 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.6 GB | – | ~120 |
| 24 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.6 GB | – | ~210 |
| 32 GB VRAM | Runs on GPU | Q6_K (≈ lossless) | 4.6 GB | – | ~340 |
Ready-made quantizations on Hugging Face: ThePun1sher/ovis2.5-test-gguf · litert-community/Ovis2.5-2B
Benchmark results
Epoch AI has not published results for Ovis2.5 2B yet. New models are usually evaluated within days to weeks.
Links
Announcement · Hugging Face: ATH-MaaS/Ovis2.5-2B
More from Qwen
Qwen3.8 Omni Flash · Qwen3.8 Max (0902) · Qwen3.8 Flash · Qwen3.8 Flash Next · Qwen 3.8 27B · Qwen3.8-2.4T-A95B · Qwen 3.8 Max · Qwen3.7 Flash