20 GB VRAM (+4)
B
Adds memory headroom for longer context windows and future model growth.35.3 tok/s decode
Adds memory headroom for longer context windows and future model growth.
~$1,250 MSRP
Can Phi 3 Medium 14B run on Tesla P100 16GB?
YES — Tight Fit
B63Good
○Estimated from fit model
Phi 3 Medium 14B needs ~14.4 GB VRAM. Tesla P100 16GB has 16.0 GB. With Q4_K_M quantization, expect ~51 tok/s.
Runtime: OllamaCapacity: TightBandwidth: MediumStack: BasicBottleneck: Balanced
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.
Select quantization to explore
Q4_K_M (Medium quality) — 14.4 GB, 54.4 tok/s, Tight fit
14.4 GB required16.0 GB available
90% VRAM used
Fit status
Tight fit
Decode
54.4 tok/s
TTFT
3561 ms
Safe context
24K
Memory
14.4 GB / 16.0 GB
Memory breakdown
Weights8.5 GB
KV Cache3.1 GB
Runtime1.2 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsPhi 3 Medium 14B on Tesla P100 16GB
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: 54.4 tok/s decode · 3.6s TTFT (warm) · 136 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
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
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | B | Runs well | 54.4 tok/s | 1942 ms | 24K |
| Coding | B | Tight fit | 50.6 tok/s | 3828 ms | 24K |
| Agentic Coding | C | Very compromised (needs ~0.7 GB host RAM) | 32.8 tok/s | 8585 ms | 24K |
| Reasoning | B | Tight fit | 54.4 tok/s | 4209 ms | 24K |
| RAG | C | Very compromised (needs ~0.7 GB host RAM) | 32.8 tok/s | 10731 ms |
Quantization options
How Phi 3 Medium 14B (14B params) fits at each quantization level on Tesla P100 16GB (16.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.5 GB | Low | B60 |
Q3_K_S | 3 | 6.9 GB | Low | B62 |
NVFP4 | 4 |
Get started
Copy-paste commands to run Phi 3 Medium 14B on your machine.
Run
ollama run phi3:mediumUpgrade options
Hardware that runs Phi 3 Medium 14B well
24 GB VRAM (+8)936 GB/s (+204)
B
Raises estimated decode speed by about 52%.82.5 tok/s decode
Raises estimated decode speed by about 52%.
Adds memory headroom for longer context windows and future model growth.
~$1,499 MSRP
24 GB VRAM (+8)
B
Raises estimated decode speed by about 31%.71.1 tok/s decode
Raises estimated decode speed by about 31%.
Adds memory headroom for longer context windows and future model growth.
~$1,599 MSRP