Can Phi-4-reasoning-plus 14B run on Gaudi 3 128GB?

YES — Runs Great

S86Excellent

○Estimated from fit model

Phi-4-reasoning-plus 14B needs ~25.7 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~206 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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) — 25.7 GB, 205.8 tok/s, Runs well

25.7 GB required128.0 GB available

20% VRAM used

Fit status

Runs well

Decode

205.8 tok/s

TTFT

941 ms

Safe context

33K

Memory

25.7 GB / 128.0 GB

Memory breakdown

Weights9.0 GB

KV Cache3.1 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsPhi-4-reasoning-plus 14B on Gaudi 3 128GB
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: 205.8 tok/s decode · 941ms TTFT (warm) · 515 tok/s prefill

What limits this setup

The raw memory story may look fine, but the software ecosystem is still a constraint here.

Runtime ecosystem is narrower than CUDA

Intel GPUs can look attractive on memory per dollar, but local AI tooling, kernels, and model coverage are still broader and easier on CUDA today.

Best improvement path

Prefer CUDA if you want the path of least resistance

If your goal is maximum runtime coverage, easier troubleshooting, and better support for new local AI releases, CUDA is usually still the safer upgrade path.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	205.8 tok/s	513 ms	33K
Coding	S	Runs well	205.8 tok/s	941 ms	33K
Agentic Coding	S	Runs well	205.8 tok/s	1368 ms	33K
Reasoning	S	Runs well	205.8 tok/s	1112 ms	33K
RAG	S	Runs well	205.8 tok/s	1710 ms	33K

Quantization options

How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.7 GB	Low	A78
Q3_K_S	3	7.2 GB	Low	A78
NVFP4	4

Get started

Copy-paste commands to run Phi-4-reasoning-plus 14B on your machine.

Run

ollama run phi4-reasoning

Your hardware

More models your Gaudi 3 128GB can run

Model	Params	Grade	Decode	Capabilities
👁 Mistral Devstral 2 123B Instruct	123B	S	37.5 tok/s
👁 Alibaba Qwen3-Coder 30B A3B Instruct	30.5B	S

Frequently asked questions

See all results for Gaudi 3 128GB See all hardware for Phi-4-reasoning-plus 14B

URL: https://willitrunai.com/can-run/phi-4-reasoning-plus-14b-on-gaudi-3-128gb

⇱