All tasks / Models
Ling-3.0-flash-VL
inclusionAI's open-weights vision-language MoE (124B total, 5.5B active) built on Ling 3.0 Flash, MIT licence.
- inclusionAI
- Open weights
- Released Sep 2026
Where it ranks
- AImage understandingModels · Local · 79% on Artificial Analysis MMMU-Pro (independent evaluation) (secondary benchmark)
Facts
- Vendor
- inclusionAI
- Family
- Ling Flash VL
- Released
- Sep 2026
- Weights
- Open: download and run it yourself
- License
- MIT
- Parameters
- 124.8B (5.5B active)
- GPU memory to run locally
- ~73 GB (124.8B total (HF safetensors); 4-bit ≈ 124.8 × 0.57 + 1.5 ≈ 73 GB, estimate.)
- API price
- $0.06 in / $0.18 out per 1M tokens (DeepInfra endpoint on OpenRouter (fp16).)
- Access
- Free (open weights)
- Last verified
- 19 Oct 2026
Price from openrouter.ai, 19 Oct 2026.
Benchmark results
| Benchmark | Result | Entry on the leaderboard | As of | Source |
|---|---|---|---|---|
| Artificial Analysis MMMU-Pro (independent evaluation) | 79% | Ling-3.0-flash-VLRaw fraction 0.7896 from the model data embedded in https://artificialanalysis.ai/leaderboards/models, converted to percent; rank 34 of 124 entries with an MMMU-Pro result; no last-updated date shown. | 19 Oct 2026 | artificialanalysis.ai |
Where you can use it
- SOpenRouterRuntimes & gateways · Cloud