Ling Models — Hardware Requirements
5 Ling models from Inclusion AI and the community, from the smallest that runs in 5.5 GB of VRAM at Q4 up to 572.1B parameters. Every row links to full quantization tables and GPU compatibility.
All Ling Models by Size
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Ling 3.0 Tiny | 7.9B | 5.5 GB | 131K | ||
| Ling 3.0 Flash VL | 124.8B | 76 GB | 131K | ||
| Ling 3.0 Flash | 127.5B | 77.6 GB | 262K | ||
| Ling 3.1 Flash | 572.1B | 344.9 GB | 262K | ||
| Ling 3.1 Flash 1019 | 572.1B | 344.9 GB | 262K |
Community variants and fine-tunes(2)
| Model | Params | Runs from (Q4) | Context | Publisher | Quant downloads |
|---|---|---|---|---|---|
| Ling 3.0 Flash Fin | 127.5B | 77.6 GB | 262K | ||
| Ling 3.0 Flash Sante | 127.5B | 77.6 GB | 262K |
Frequently Asked Questions
- How much VRAM do I need to run a Ling model?
- The smallest Ling model, Ling 3.0 Tiny, runs from 5.5 GB of VRAM at Q4_K_M (smaller low-bit quantizations start at 2.8 GB with a noticeable quality loss). Larger family members need proportionally more — see the table above for every model.
- Which Ling models can I run on a 16 GB GPU?
- 1 of 7 Ling models fit in 16 GB of VRAM at Q4_K_M, including Ling 3.0 Tiny.
- What is the most popular Ling model to run locally?
- Ling 3.0 Tiny is the most downloaded Ling model in local-friendly quantized formats. It runs from 5.5 GB of VRAM at Q4_K_M.