bigcode models
1 bigcode model from bigcode on Hugging Face, from 1.1B to 1.1B parameters, published by bigcode in F16, with a 2K-token context. The smallest official model, gpt_bigcode-santacoder, needs about 2.5 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Pick a size
One row per official bigcode size: the VRAM it needs at each precision, the cheapest GPU that holds it today, and the KV cache for a 32K-token context.
| Model | Parameters | Native VRAM | FP8 VRAM | INT4 VRAM | Live GPU fit (native) | Est. $/hr | KV cache at 32K |
|---|---|---|---|---|---|---|---|
| gpt_bigcode-santacoder | 1.1B | 2.5 GB | 1.3 GB | 0.6 GB | RTX 3070 | $0.088/hr | 0.38 GB |
VRAM is weights times a flat 1.2 overhead; the KV cache is a separate per-model figure at 16-bit, shown where the architecture is published. See the methodology.
Official models (1)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| gpt_bigcode-santacoder | 1.1B | F16 | 2.5 GB | RTX 3070 | $0.088/hr |
VRAM is for the precision the model is published in: the weights times a flat 1.2 overhead, with the KV cache not included. See the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
More from bigcode
- StarCoder2 (2 models)