Can Phi 3 Medium 14B run on Radeon Pro W6800 32GB?

YES — Runs Great

B60Good

○Estimated from fit model

Phi 3 Medium 14B needs ~15.7 GB VRAM. Radeon Pro W6800 32GB has 32.0 GB. With Q4_K_M quantization, expect ~36 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: MediumStack: StandardBottleneck: Balanced

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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 15.7 GB, 36.1 tok/s, Runs well

15.7 GB required32.0 GB available

49% VRAM used

Fit status

Runs well

Decode

36.1 tok/s

TTFT

5364 ms

Safe context

102K

Memory

15.7 GB / 32.0 GB

Memory breakdown

Weights8.5 GB

KV Cache3.1 GB

Runtime0.9 GB

Headroom3.2 GB

See how fast it feels

See how fast it feelsPhi 3 Medium 14B on Radeon Pro W6800 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: 36.1 tok/s decode · 5.4s TTFT (warm) · 90 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	36.1 tok/s	2926 ms	102K
Coding	B	Runs well	36.1 tok/s	5364 ms	102K
Agentic Coding	B	Runs well	36.1 tok/s	7802 ms	102K
Reasoning	B	Runs well	36.1 tok/s	6339 ms	102K
RAG	B	Runs well	36.1 tok/s	9753 ms	102K