Granite Docling models
1 Granite Docling model from IBM on Hugging Face, from 258M to 258M parameters, published by IBM in BF16, with a 8K-token context. The smallest official model, granite-docling-258M, needs about 0.6 GB of VRAM at its published precision; the cheapest live fit is RTX 4070 Super at $0.121/hr.
Part of the Granite series
Pick a size
One row per official Granite Docling 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 |
|---|---|---|---|---|---|---|---|
| granite-docling-258M | 258M | 0.6 GB | 0.3 GB | 0.1 GB | RTX 4070 Super | $0.121/hr | 0.70 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 (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| granite-docling-258M | 258M | BF16 | 0.6 GB | RTX 4070 Super | $0.121/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 IBM
- Granite 4 (19 models)
- Granite Speech (7 models)
- Granite 3 (9 models)
