Ling models
3 Ling models from inclusionAI on Hugging Face, from 7.9B to 127.5B parameters, published by inclusionAI in BF16, with contexts from 32K to 256K tokens. The smallest official model, Ling-3.0-tiny, needs about 17.6 GB of VRAM at its published precision; the cheapest live fit is RTX A5000 at $0.176/hr.
Pick a size
One row per official Ling size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| Ling-3.0-tiny | 7.9B | 17.6 GB | 8.8 GB | 4.4 GB | RTX A5000 | $0.176/hr | 0.84 GB |
| Ling-mini-2.0 | 16.3B | 36.3 GB | 18.2 GB | 9.1 GB | RTX A6000 | $0.363/hr | 1.3 GB |
| Ling-3.0-flash | 127.5B | 285 GB | 142 GB | 71.2 GB | RTX A6000 × 6 | $2.18/hr | 1.5 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (3)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| Ling-3.0-tiny | 7.9B | BF16 | 17.6 GB | RTX A5000 | $0.176/hr |
| Ling-mini-2.0 | 16.3B | BF16 | 36.3 GB | RTX A6000 | $0.363/hr |
| Ling-3.0-flash | 127.5B | BF16 | 285 GB | RTX A6000 × 6 | $2.18/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from inclusionAI
- LLaDA (5 models)
- inclusionAI (2 models)