Microsoft on NVIDIA Ampere
Can I run Phi-4 14B on an RTX 3060 12GB?
Not at Q4_K_M — it needs 10.8 GB against 10.5 GB available. Drop to Q4_K_S and it fits, at about 25.7 tokens per second.
Won't fit
10.8 GB of 10.5 GB · 103%011 GB
Weights
8.4 GB
KV cache
1.6 GB
Runtime overhead
0.8 GB
Over the limit
0.3 GB
Short by 0.3 GB. You can run it with 38 of 40 layers on the RTX 3060 12GB and the rest in system RAM, at roughly 19.9 tok/s — usable for batch work, painful for chat. A smaller quantisation or a shorter context is usually the better trade.
Generation19.9tok/s
Prompt processing357tok/s
Max context6Ktokens
KV per 1K tokens0GB
Every quantisation of Phi-4 14B on a RTX 3060 12GB
Highlighted row is the highest quality that still fits at 8K context.
| Quantisation | bpw | Weights | Total | Verdict | Max ctx | tok/s |
|---|---|---|---|---|---|---|
| FP16 / BF16 | 16.00 | 27.4 GB | 29.8 GB | Won't fit | — | 1.83 |
| INT8 / W8A8 | 8.50 | 14.3 GB | 16.7 GB | Won't fit | — | 4.83 |
| Q8_0 (GGUF) | 8.50 | 14.3 GB | 16.7 GB | Won't fit | — | 4.83 |
| FP8 (E4M3) | 8.00 | 13.7 GB | 16.1 GB | Won't fit | — | 5.23 |
| Q6_K | 6.56 | 11.2 GB | 13.6 GB | Won't fit | — | 7.83 |
| Q5_K_M | 5.67 | 9.7 GB | 12.1 GB | Won't fit | — | 11.8 |
| Q5_K_S | 5.52 | 9.4 GB | 11.8 GB | Won't fit | 1K | 13.0 |
| AWQ 4-bit | 4.25 | 8.7 GB | 11.1 GB | Won't fit | 5K | 17.6 |
| GPTQ 4-bit | 4.25 | 8.7 GB | 11.1 GB | Won't fit | 5K | 17.6 |
| MXFP4 | 4.25 | 8.7 GB | 11.1 GB | Won't fit | 5K | 17.6 |
| Q4_K_M | 4.85 | 8.4 GB | 10.8 GB | Won't fit | 6K | 19.9 |
| Q4_K_S | 4.58 | 7.9 GB | 10.3 GB | Fits, but tight | 9K | 25.7 |
| Q4_0 | 4.55 | 7.9 GB | 10.3 GB | Fits, but tight | 9K | 25.8 |
| IQ4_XS | 4.25 | 7.4 GB | 9.8 GB | Fits, but tight | 11K | 27.3 |
| Q3_K_M | 3.91 | 6.9 GB | 9.3 GB | Runs comfortably | 14K | 29.2 |
| IQ3_M | 3.70 | 6.5 GB | 8.9 GB | Runs comfortably | 16K | 30.5 |
| IQ3_XXS | 3.06 | 5.5 GB | 7.9 GB | Runs comfortably | 16K | 35.4 |
| Q2_K | 2.63 | 4.8 GB | 7.2 GB | Runs comfortably | 16K | 39.7 |
| IQ2_XXS | 2.06 | 3.9 GB | 6.3 GB | Runs comfortably | 16K | 47.2 |
| IQ1_M | 1.75 | 3.4 GB | 5.8 GB | Runs comfortably | 16K | 52.7 |