What GPU do I need to run EleutherAI/pythia-1.4b?
1.5B parameters, published in F16. View on Hugging Face
pythia-1.4b is published by EleutherAI on Hugging Face, with 72,766 downloads and 27 likes to date. It's a GPTNeoXForCausalLM model built for text-generation, published natively in F16.
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 pythia-1.4b at its published (F16) precision: 1× P4 on akash, at $0.032/hr per GPU ($0.032/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 EleutherAI models
- pythia-160m (213M, F16)
- gpt-neox-20b (20.7B, F16)
- gpt-neo-125m (150M, F32)
- pythia-160m-deduped (213M, F16)
- pythia-410m (506M, F16)
- pythia-410m-deduped (506M, F16)
