What GPU do I need to run EleutherAI/pythia-160m?
213M parameters, published in F16. View on Hugging Face
Set up pythia-160mpythia-160m is published by EleutherAI on Hugging Face, with 3,494,493 downloads and 45 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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run pythia-160m at its published (F16) precision: 1× RTX 3070 on simplepod, at $0.050/hr per GPU ($0.050/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
pythia-160m: common questions
How much VRAM does pythia-160m need?
0.5 GB at FP16, 0.2 GB at FP8 (quantized), 0.1 GB at INT4 (quantized). All of those sit under 6 GB, the smallest capacity this page reasons about, so VRAM is not what limits where this model runs. The 0.4 GB of weights plus inference overhead is the whole requirement.
How many copies of pythia-160m fit on one RTX 3070?
16, by VRAM alone. That card carries 8.0 GB and one copy needs 0.5 GB at FP16, on a live rate of $0.050/hr for the whole card. Throughput is not modelled here, so 16 copies is not 16 times the requests served.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More EleutherAI models
- gpt-neox-20b (20.7B, F16)
- pythia-160m-deduped (213M, F16)
- gpt-neo-125m (150M, F32)
- pythia-410m (506M, F16)
- pythia-1.4b (1.5B, F16)
- pythia-1b (1.1B, F16)
