What GPU do I need to run ibm-granite/granite-3b-code-base-2k?
3.5B parameters, published in BF16. View on Hugging Face
Set up granite-3b-code-base-2kgranite-3b-code-base-2k is published by ibm-granite on Hugging Face, with 40,019 downloads and 38 likes to date. It's a LlamaForCausalLM model built for text-generation, published natively in BF16.
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.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 6.5 GB | 7.8 GB | RTX 5060 Ti | 1 | $0.110/hr |
| FP8 (quantized) | 3.2 GB | 3.9 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 1.6 GB | 1.9 GB | RTX 5060 Ti | 1 | $0.110/hr |
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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run granite-3b-code-base-2k at its published (BF16) precision: 1× RTX 5060 Ti, at $0.110/hr per GPU ($0.110/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
granite-3b-code-base-2k: common questions
Does granite-3b-code-base-2k fit on a 8 GB GPU?
Yes. At BF16 it needs 7.8 GB of VRAM, so an 8 GB card holds it with 0.2 GB to spare. A 6 GB card is not enough for it at BF16.
How many copies of granite-3b-code-base-2k fit on one RTX 5060 Ti?
2, by VRAM alone. That card carries 16.0 GB and one copy needs 7.8 GB at BF16, on a live rate of $0.110/hr for the whole card. Throughput is not modelled here, so 2 copies is not 2 times the requests served.
What is the least VRAM granite-3b-code-base-2k can run in?
1.9 GB, at INT4 (quantized), which fits a 6 GB card, against 7.8 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More Granite models
- granite-speech-5.0-470m-turboctc (473M, BF16)
- granite-speech-5.0-470m-turboctc-nc (473M, BF16)
- granite-docling-258M (258M, BF16)
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
