VOOZH about

URL: https://willitrunai.com/can-run/phi-4-reasoning-plus-14b-on-arc-a770-16gb

⇱

Can Phi-4-reasoning-plus 14B run on Intel Arc A770 16GB?

YES — Tight Fit

S90Excellent
○Estimated from fit model

Phi-4-reasoning-plus 14B needs ~14.5 GB VRAM. Intel Arc A770 16GB has 16.0 GB. With Q4_K_M quantization, expect ~30 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.

Capabilities:

Select quantization to explore

Q4_K_M (Medium quality) — 14.5 GB, 30.2 tok/s, Tight fit
14.5 GB required16.0 GB available
91% VRAM used

Fit status

Tight fit

Decode

30.2 tok/s

TTFT

6408 ms

Safe context

24K

Memory

14.5 GB / 16.0 GB

Memory breakdown

Weights9.0 GB
KV Cache3.1 GB
Runtime0.9 GB
Headroom1.6 GB

See how fast it feels

See how fast it feelsPhi-4-reasoning-plus 14B on Intel Arc A770 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: 30.2 tok/s decode · 6.4s TTFT (warm) · 76 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

WorkloadGradeFitDecodeTTFTContext
ChatSRuns well30.2 tok/s3495 ms24K
CodingSTight fit30.2 tok/s6408 ms24K
Agentic CodingAVery compromised (needs ~0.8 GB host RAM)18.6 tok/s15136 ms24K
ReasoningSTight fit30.2 tok/s7573 ms24K
RAGAVery compromised (needs ~0.8 GB host RAM)18.6 tok/s18920 ms

Quantization options

How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on Intel Arc A770 16GB (16.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
5.7 GB
LowS89
Q3_K_S
3
7.2 GB
LowS91
NVFP4
4

Get started

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

Run

ollama run phi4-reasoning

Frequently asked questions

See all results for Intel Arc A770 16GBSee all hardware for Phi-4-reasoning-plus 14B
24K
8.2 GB
Medium
S91
Q4_K_M
4
9.0 GB
MediumS91
Q5_K_M
5
10.6 GB
HighS91
Q6_KBest for your GPU
6
12.1 GB
HighS90
Q8_0
8
15.7 GB
Very HighF0
F16
16
30.1 GB
MaximumF0

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.