Granite 4.0 Small-H 32B-A9B — VRAM Requirements
Written by Jakub Rusinowski · Last updated August 15, 2026
How much GPU VRAM you need to run IBM Granite 4.0 Granite 4.0 Small-H 32B-A9B by IBM locally, a 32B-parameter model. Figures are quantized weights + KV cache + framework overhead, computed from the model's parameter count and published architecture — not a throughput model. See /en/methodology.
Granite 4.0 Small-H 32B-A9B needs about 20 GB VRAM at Q4_K_M.
VRAM by Quantization
| Quant | Bits/weight | Weights | Total VRAM |
|---|---|---|---|
| Q2_K | 2.63 | 10.5 GB | 11.3 GB |
| Q3_K_M | 3.41 | 13.6 GB | 14.4 GB |
| Q4_K_M | 4.83 | 19.3 GB | 20.1 GB |
| Q5_K_M | 5.67 | 22.7 GB | 23.5 GB |
| Q6_K | 6.56 | 26.2 GB | 27.0 GB |
| Q8_0 | 8.50 | 34.0 GB | 34.8 GB |
| F16 | 16.00 | 64.0 GB | 64.8 GB |
Switch quantization in the interactive calculator, or see the full IBM Granite 4.0 model page.
Add this badge to your model card
Model creators: paste this into your Hugging Face model card README to link readers straight to this VRAM breakdown.
[](https://llmconfigurator.com/en/vram-calculator/granite-4-32b-a9b-h?utm_source=badge&utm_medium=referral&utm_campaign=readme_badge&utm_content=granite-4-32b-a9b-h)Estimates only — actual VRAM varies with context length, batch size, runtime and KV-cache settings.