Can Phi-4 Mini Reasoning 4B run on Gaudi 3 128GB?

YES — Runs Great

A80Great

○Estimated from fit model

Phi-4 Mini Reasoning 4B needs ~17.5 GB VRAM. Gaudi 3 128GB has 128.0 GB. With Q4_K_M quantization, expect ~53 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) — 17.5 GB, 53.2 tok/s, Runs well

17.5 GB required128.0 GB available

14% VRAM used

Fit status

Runs well

Decode

53.2 tok/s

TTFT

3639 ms

Safe context

131K

Memory

17.5 GB / 128.0 GB

Memory breakdown

Weights2.3 GB

KV Cache1.5 GB

Runtime0.9 GB

Headroom12.8 GB

See how fast it feels

See how fast it feelsPhi-4 Mini Reasoning 4B 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: 53.2 tok/s decode · 3.6s TTFT (warm) · 133 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	A	Runs well	53.2 tok/s	1985 ms	131K
Coding	A	Runs well	53.2 tok/s	3639 ms	131K
Agentic Coding	A	Runs well	53.2 tok/s	5293 ms	131K
Reasoning	A	Runs well	53.2 tok/s	4301 ms	131K
RAG	A	Runs well	53.2 tok/s	6617 ms	131K

Quantization options

How Phi-4 Mini Reasoning 4B (3.799999952316284B params) fits at each quantization level on Gaudi 3 128GB (128.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	1.5 GB	Low	A75
Q3_K_S	3	1.9 GB	Low	A75
NVFP4	4

Get started

Copy-paste commands to run Phi-4 Mini Reasoning 4B on your machine.

Run

ollama run phi4-mini

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 Mini Reasoning 4B

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

⇱