# Can I run Granite 4.0 H Small on Nvidia GeForce RTX 4090 (24GB)?

Updated: 2026-06-15

**Yes, it runs.** Runs at Q4_K_M using ~20.4 GB of ~23 GB usable.

- Model: 32B (MoE, 9B active), Q4_K_M 18.23 GB
- Device: 24 GB vram, ~23 GB usable for weights
- Needs ~20.4 GB at Q4_K_M; recommended quant: Q4_K_M
- Best tool on Windows: LM Studio
- Command: `ollama run granite4:small-h`

Estimate. Method: weights + KV cache + ~0.8GB overhead. Sources: https://ollama.com/library/granite4, https://ollama.com/library/granite4/tags, https://huggingface.co/unsloth/granite-4.0-h-small-GGUF, https://huggingface.co/ibm-granite/granite-4.0-h-small.

More: https://localmodel.run/can-i-run/granite-4.0-h-small/nvidia-rtx-4090-24gb