estimate, except measured file sizes
Can I run Phi-4 14B locally?
14.7B parameters. Parameter count is an estimate.
- Licence:
- not recorded
- Context:
- 16,384 tokens
- Modality:
- not recorded
- Released:
- not recorded
Architecture figures are an estimate. No config was fetched, so the VRAM line can be slightly off.
Memory per quant
KV is at 8,192 tokens. Overhead is 0.8 GB. Both are estimates. A measured file size is labelled. The last column is the cheapest machine that fits the total fully.
| Quant | File size | KV at 8K | +0.8 overhead | Total | Cheapest full fit |
|---|---|---|---|---|---|
| Q8 | 15.7 GB est. | 1.7 GB est. | 0.8 GB est. | 18.2 GB est. | GeForce RTX 3090 24GB, €1,224 (used (median of sold listings)) |
| Q4 | 8.8 GB est. | 1.7 GB est. | 0.8 GB est. | 11.3 GB est. | GeForce RTX 3060 12GB, €257 (used (median of sold listings)) |
Cheapest rig that fits
Q4, full: GeForce RTX 3060 12GB, €257 (used (median of sold listings))
Q4, slow, partly in system RAM: Nothing on our list of 29 machines fits this quant.