Phi 3 Medium 14B needs ~13.7 GB VRAM. RTX A2000 12GB has 12.0 GB. With Q4_K_M quantization, expect ~16 tok/s.
Operating mode
Interactive favors responsiveness, while light API and scale-out lean harder on serving readiness. The fit stays the same, but the recommendation lens changes.
Current mode
Balanced
Balanced for general local use. Keeps the ranking neutral across personal and serving workflows.
Select quantization to explore
1.7 GB over capacity — needs offload or smaller quantization
Fit status
Very compromised (needs ~1.1 GB host RAM)
Decode
16.1 tok/s
TTFT
12050 ms
Safe context
7K
Memory
13.7 GB / 12.0 GB
Offload
10%
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.
Very little memory headroom
You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.
Remove offload with more accelerator memory
Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Buy headroom, not only minimum fit
A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.
Increase host RAM if you keep offloading
This setup may need roughly 1.1 GB of extra host RAM just for the offloaded portion, before OS and other tools.
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs with offload (needs ~0.1 GB host RAM) | 20.6 tok/s | 5125 ms | 7K |
| Coding | C | Very compromised (needs ~1.1 GB host RAM) | 16.1 tok/s | 12050 ms | 7K |
| Agentic Coding | F | Too heavy | 10.5 tok/s | 26770 ms | 7K |
| Reasoning | C | Very compromised (needs ~1.1 GB host RAM) | 16.1 tok/s | 14241 ms | 7K |
| RAG | F | Too heavy | 10.5 tok/s | 33463 ms | 7K |
How Phi 3 Medium 14B (14B params) fits at each quantization level on RTX A2000 12GB (12.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | B63 |
Q3_K_S | 3 | 6.9 GB | Low | B63 |
NVFP4 | 4 | 7.8 GB | Medium | B63 |
Q4_K_MBest for your GPU | 4 | 8.5 GB | Medium | B63 |
Q5_K_M | 5 | 10.1 GB | High | F0 |
Q6_K | 6 | 11.5 GB | High | F0 |
Q8_0 | 8 | 15.0 GB | Very High | F0 |
F16 | 16 | 28.7 GB | Maximum | F0 |
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumアップグレードオプション
RTX 5060 Ti 16GBコスパ重視Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 111%.
〜$449 MSRP
RTX 4060 Ti 16GBコスパ最良Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 73%.
〜$499 MSRP
RTX 2000 Ada 16GBNVIDIAアップグレードRemoves host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 71%.
〜$625 MSRP
RTX A4500 20GB最大の飛躍Removes host-memory offload, which is usually the single biggest latency and throughput win.
Raises estimated decode speed by about 290%.
〜$2,000 MSRP
Yes, RTX A2000 12GB can run Phi 3 Medium 14B with a C grade (Very compromised (needs ~1.1 GB host RAM)). Expected decode speed: 16.1 tok/s.
Phi 3 Medium 14B (14B parameters) requires approximately 13.7 GB of memory with Q4_K_M quantization.
The recommended quantization for Phi 3 Medium 14B is Q4_K_M, which balances quality and memory efficiency.
On RTX A2000 12GB, Phi 3 Medium 14B achieves approximately 16.1 tokens per second decode speed with a time-to-first-token of 12050ms using Q4_K_M quantization.
For coding workloads, Phi 3 Medium 14B on RTX A2000 12GB receives a C grade with 16.1 tok/s and 7K context.
On RTX A2000 12GB, Phi 3 Medium 14B can safely use up to 7K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.
Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.
Paste this snippet into any page to show a live fit card.
<iframe src="https://willitrunai.com/embed/phi-3-medium-14b-on-a2000-12gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>
Preview: