RX 7900 XT 20GBBudget pick
20 GB VRAM (+4)800 GB/s (+224)
B
Raises estimated decode speed by about 43%.60.4 tok/s decode
Raises estimated decode speed by about 43%.
Adds memory headroom for longer context windows and future model growth.
~$899 MSRP
Can Phi 3 Medium 14B run on RX 6950 XT 16GB?
YES — Tight Fit
B62Good
○Estimated from fit model
Phi 3 Medium 14B needs ~14.1 GB VRAM. RX 6950 XT 16GB has 16.0 GB. With Q4_K_M quantization, expect ~42 tok/s.
Runtime: llama.cppCapacity: TightBandwidth: MediumStack: StandardBottleneck: 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) — 14.1 GB, 42.1 tok/s, Tight fit
14.1 GB required16.0 GB available
88% VRAM used
Fit status
Tight fit
Decode
42.1 tok/s
TTFT
4604 ms
Safe context
26K
Memory
14.1 GB / 16.0 GB
Memory breakdown
Weights8.5 GB
KV Cache3.1 GB
Runtime0.9 GB
Headroom1.6 GB
See how fast it feels
See how fast it feelsPhi 3 Medium 14B on RX 6950 XT 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: 42.1 tok/s decode · 4.6s TTFT (warm) · 105 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 | B | Runs well | 42.1 tok/s | 2511 ms | 26K |
| Coding | B | Tight fit | 42.1 tok/s | 4604 ms | 26K |
| Agentic Coding | C | Runs with offload (needs ~0.6 GB host RAM) | 27.3 tok/s | 10325 ms | 26K |
| Reasoning | B | Tight fit | 42.1 tok/s | 5441 ms | 26K |
| RAG | C | Runs with offload (needs ~0.6 GB host RAM) | 27.3 tok/s | 12906 ms |
Quantization options
How Phi 3 Medium 14B (14B params) fits at each quantization level on RX 6950 XT 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
RX 7900 XTX 24GBBest value
24 GB VRAM (+8)960 GB/s (+384)
B
Raises estimated decode speed by about 107%.87 tok/s decode
Raises estimated decode speed by about 107%.
Adds memory headroom for longer context windows and future model growth.
~$999 MSRP
AMD Instinct MI100 32GBAMD upgrade
32 GB VRAM (+16)1228 GB/s (+652)
B
Raises estimated decode speed by about 139%.100.5 tok/s decode
Raises estimated decode speed by about 139%.
Adds memory headroom for longer context windows and future model growth.
~$11,500 MSRP