Phi-1 models
2 Phi-1 models from Microsoft on Hugging Face, from 1.4B to 1.4B parameters, published by Microsoft in F16, with a 2K-token context. The smallest official model, phi-1, needs about 3.2 GB of VRAM at its published precision; the cheapest live fit is RTX 3070 at $0.088/hr.
Part of the Phi series · Next generation: Phi-2
Pick a size
One row per official Phi-1 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 |
|---|---|---|---|---|---|---|---|
| phi-1_5 | 1.4B | 3.2 GB | 1.6 GB | 0.8 GB | RTX 3070 | $0.088/hr | 6.0 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 (2)
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| phi-1 | 1.4B | F16 | 3.2 GB | RTX 3070 | $0.088/hr |
| phi-1_5 | 1.4B | F16 | 3.2 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.