40 GB VRAM (+8)1555 GB/s (+979)
C
Raises estimated decode speed by about 183%.142.8 tok/s decode
Raises estimated decode speed by about 183%.
Adds memory headroom for longer context windows and future model growth.
~$10,000 MSRP
Can Phi 4 reasoning vision 15B run on RTX 5000 Ada 32GB?
YES — Runs Great
C50Usable
○Estimated from fit model
Phi 4 reasoning vision 15B needs ~15.3 GB VRAM. RTX 5000 Ada 32GB has 32.0 GB. With Q4_K_M quantization, expect ~50 tok/s.
Runtime: OllamaCapacity: RoomyBandwidth: 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) — 15.3 GB, 50.4 tok/s, Runs well
15.3 GB required32.0 GB available
48% VRAM used
Fit status
Runs well
Decode
50.4 tok/s
TTFT
3844 ms
Safe context
168K
Memory
15.3 GB / 32.0 GB
Memory breakdown
Weights9.2 GB
KV Cache1.8 GB
Runtime1.2 GB
Headroom3.2 GB
See how fast it feels
See how fast it feelsPhi 4 reasoning vision 15B on RTX 5000 Ada 32GB
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: 50.4 tok/s decode · 3.8s TTFT (warm) · 126 tok/s prefill
What limits this setup
This setup is broadly balanced for this model.
No major red flags
This recommendation has enough memory headroom and acceptable estimated speed for the selected workload.
Best improvement path
Performance by workload
| Workload | Grade | Fit | Decode | TTFT | Context |
|---|---|---|---|---|---|
| Chat | C | Runs well | 50.4 tok/s | 2097 ms | 168K |
| Coding | C | Runs well | 50.4 tok/s | 3844 ms | 168K |
| Agentic Coding | C | Runs well | 50.4 tok/s | 5592 ms | 168K |
| Reasoning | C | Runs well | 50.4 tok/s | 4543 ms | 168K |
| RAG | C | Runs well | 50.4 tok/s | 6990 ms | 168K |
Quantization options
How Phi 4 reasoning vision 15B (15B params) fits at each quantization level on RTX 5000 Ada 32GB (32.0 GB usable).
| Quant | Bits | VRAM | Quality | Fit |
|---|---|---|---|---|
Q2_K | 2 | 5.9 GB | Low | C44 |
Q3_K_S | 3 | 7.4 GB | Low | C45 |
NVFP4 | 4 | 8.4 GB | Medium | C45 |
Q4_K_M | 4 | 9.2 GB | Medium | C45 |
Q5_K_M | 5 | 10.8 GB | High | C46 |
Q6_K | 6 | 12.3 GB | High | C47 |
Q8_0Best for your GPU | 8 | 16.1 GB | Very High | C49 |
F16 | 16 | 30.7 GB | Maximum | F0 |
Get started
Copy-paste commands to run Phi 4 reasoning vision 15B on your machine.
Run
lms load hf-jamesburton--phi-4-reasoning-vision-15b-gguf && lms server startUpgrade options