What GPU do I need to run ibm-granite/granite-4.1-8b-fp8?
8.8B parameters, published in F8_E4M3. View on Hugging Face
granite-4.1-8b-fp8 is published by ibm-granite on Hugging Face, with 22,322 downloads and 14 likes to date. It's a GraniteForCausalLM model built for text-generation, published natively in F8_E4M3.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run granite-4.1-8b-fp8 at its published (F8_E4M3) precision: 1× RTX 4070 on simplepod, at $0.080/hr per GPU ($0.080/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More ibm-granite models
- granite-4.1-8b (8.8B, BF16)
- granite-4.1-30b (28.9B, BF16)
- granite-speech-4.1-2b (2.3B, BF16)
- granite-guardian-3.3-8b (8.2B, BF16)
- granite-docling-258M (258M, BF16)
- granite-4.1-3b (3.4B, BF16)
