12 GB VRAM (+1)
B
Makes the model fit on the accelerator instead of staying completely out of reach.16.2 tok/s decode
Makes the model fit on the accelerator instead of staying completely out of reach.
~$329 MSRP
Can Phi-4 14B run on RTX 2080 Ti 11GB?
YES — With NVFP4
B66Good
○Estimated from fit model
Phi-4 14B needs ~13.2 GB VRAM. RTX 2080 Ti 11GB has 11.0 GB. With NVFP4 quantization, expect ~28 tok/s.
Runtime: OllamaCapacity: OffloadBandwidth: MediumStack: BasicBottleneck: Host offload
Share:
Operating mode
Choose the run profile you care about
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.
Phi-4 14B at Q4_K_M needs 13.9 GB — too much for RTX 2080 Ti 11GB (11.0 GB). Runs at NVFP4 (13.2 GB) with medium quality. 3 quantization levels fit.
Select quantization to explore
Q4_K_M (Medium quality) — 13.9 GB, exceeds 11.0 GB available
13.9 GB required11.0 GB available
126% VRAM needed
2.9 GB over capacity — needs offload or smaller quantization
Fit status
Too heavy
Decode
22.0 tok/s
TTFT
8792 ms
Safe context
4K
Memory
13.9 GB / 11.0 GB
Offload
20%
Memory breakdown
Weights8.5 GB
KV Cache3.1 GB
Runtime1.2 GB
Headroom1.1 GB
See how fast it feels
With memory offload — actual speed may be lowerSee how fast it feelsPhi-4 14B on RTX 2080 Ti 11GB
1st promptCold start — includes initialization
>Solve: If a train travels at 60 mph for 2.5 hours, how far does it go?
Let me work through this step by step.
Given information:
- Speed = 60 mph (miles per hour)
- Time = 2.5 hours
Formula: Distance = Speed x Time
Calculation:
Distance = 60 mph x 2.5 h
= 150 miles
The train travels 150 miles.
Double-check: at 60 mph the train covers 60 miles each hour. In half an hour it covers 30 miles. So in 2.5 hours: 60 + 60 + 30 = 150 miles. Confirmed.
2nd promptWarm — model ready, no init overhead
>What if the train stops for 20 minutes halfway?
The stop doesn't change the total distance covered while moving, but it affects total trip time.
Breakdown:
- First half: 1.25 hours at 60 mph = 75 miles
- Stop: 20 minutes (no distance)
- Second half: 1.25 hours at 60 mph = 75 miles
Total distance: 150 miles (same)
Total time: 2.5 h + 0.33 h = 2.83 hours
Average speed: 150 / 2.83 = 53 mph
The distance stays the same but average speed drops to 53 mph because of the stop.
Estimated: 22.0 tok/s decode · 8.8s TTFT (warm) · 55 tok/s prefill
What limits this setup
It fits through host-memory offload, and offload is the main reason performance drops.
CPU or host-memory offload is active
About 20% 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.
Older PCIe generation
PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.
Best improvement path
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 1.3 GB of extra host RAM just for the offloaded portion, before OS and other tools.
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | A | Very compromised (needs ~0.9 GB host RAM) | 28.4 tok/s | 3714 ms | 4K |
| Coding | F | Too heavy | 22.0 tok/s | 8792 ms | 4K |
| Agentic Coding | F | Too heavy | 14.2 tok/s | 19779 ms | 4K |
| Reasoning | F | Too heavy | 22.0 tok/s | 10390 ms | 4K |
| RAG | F | Too heavy | 14.2 tok/s | 24724 ms | 4K |
Quantization options
How Phi-4 14B (14B params) fits at each quantization level on RTX 2080 Ti 11GB (11.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | A84 |
Q3_K_S | 3 | 6.9 GB | Low | A84 |
NVFP4Best for your GPU |
Get started
Copy-paste commands to run Phi-4 14B on your machine.
Run
ollama run phi4Upgrade options
Hardware that runs Phi-4 14B well
16 GB VRAM (+5)
A
Makes the model fit on the accelerator instead of staying completely out of reach.35 tok/s decode
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$449 MSRP
16 GB VRAM (+5)
A
Makes the model fit on the accelerator instead of staying completely out of reach.26.5 tok/s decode
Makes the model fit on the accelerator instead of staying completely out of reach.
Removes host-memory offload, which is usually the single biggest latency and throughput win.
~$499 MSRP