granite-4.0-h-small GPU Requirements: VRAM & Cheapest GPU
granite-4.0-h-small has about 32.2B parameters. See exactly how much GPU memory it needs at FP16, INT8, and INT4, and the cheapest GPU to run it, with live hourly pricing from 5+ data center partners.
To run granite-4.0-h-small for inference at FP16, you need roughly 70 GB of VRAM. The cheapest fit on Spheron is A100 80GB at about $0.79/hr. Quantize to INT4 to run it on a smaller, cheaper GPU.
Estimated peak VRAM including weights, activations, and KV cache. Add 10% headroom for production traffic.
- 01$0.79/hr$0.79/hr1× A100 80GBCHEAPESTAmpere · HBM2e
- 02$0.86/hr$0.86/hr1× RTX PRO 6000 96GBBlackwell · GDDR7
- 03$0.61/hr$1.22/hr2× L40S 48GBAda Lovelace · GDDR6
- 04$1.43/hr$1.43/hr1× H100 80GBHopper · HBM3
- 05$1.77/hr$1.77/hr1× H200 141GBHopper · HBM3e
Live pricing aggregated from 5+ data center partners. Per-minute billing, no commitments.
VRAM required to run granite-4.0-h-small
Estimated peak VRAM at context length 4,096 and batch size 1, including weights, activations, and KV cache. Quantizing to INT8 (Q8) or INT4 (Q4) cuts memory roughly in half and in quarter.
| Precision | Inference | LoRA fine-tune | Full fine-tune |
|---|---|---|---|
| FP16 | 70 GB | 105 GB | 281 GB |
| INT8 | 35 GB | 53 GB | 140 GB |
| INT4 | 18 GB | 26 GB | 70 GB |
Cheapest GPU to run granite-4.0-h-small by precision
Full precision. Best quality, highest memory.
8-bit quantized. ~2x smaller, minimal quality loss.
4-bit quantized. ~4x smaller, runs on smaller GPUs.
Inference vs fine-tuning granite-4.0-h-small
Inference only holds the model weights plus a KV cache, so it is the cheapest setup. LoRA fine-tuning adds a small adapter and roughly 50% more memory. Full fine-tuning holds gradients and optimizer state on top of the weights, which is about 4x the inference footprint, so it often needs multiple GPUs even when inference fits on one. For granite-4.0-h-small, an on-demand A100 80GB instance covers inference and LoRA, while a full fine-tune needs several times that memory and often spans multiple GPUs. Check the live GPU pricing for current rates.
Deployment guideDeploy Granite 4 step by stepHands-on production setup, GPU configs, and benchmarks for granite-4.0-h-small.Read guideSimilar models
Compare GPU requirements for models in the same class.