Will It Run AI

Can Phi 4 reasoning vision 15B run on AMD Instinct MI250X 128GB?

YES — Runs Great

C46Usable
Estimated from fit model

Phi 4 reasoning vision 15B needs ~24.6 GB VRAM. AMD Instinct MI250X 128GB has 128.0 GB. With Q4_K_M quantization, expect ~210 tok/s.

Runtime: llama.cppCapacity: RoomyBandwidth: HighStack: 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) — 24.6 GB, 210.0 tok/s, Runs well
24.6 GB required128.0 GB available
19% VRAM used

Fit status

Runs well

Decode

210.0 tok/s

TTFT

922 ms

Safe context

957K

Memory

24.6 GB / 128.0 GB

Memory breakdown

Weights9.2 GB
KV Cache1.8 GB
Runtime0.9 GB
Headroom12.8 GB

See how fast it feels

See how fast it feelsPhi 4 reasoning vision 15B on AMD Instinct MI250X 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: 210.0 tok/s decode · 922ms TTFT (warm) · 525 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

WorkloadGradeFitDecodeTTFTContext
ChatCRuns well210.0 tok/s503 ms957K
CodingCRuns well210.0 tok/s922 ms957K
Agentic CodingCRuns well210.0 tok/s1341 ms957K
ReasoningCRuns well210.0 tok/s1090 ms957K
RAGCRuns well210.0 tok/s1676 ms957K

Quantization options

How Phi 4 reasoning vision 15B (15B params) fits at each quantization level on AMD Instinct MI250X 128GB (128.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
5.9 GB
LowD38
Q3_K_S
3
7.4 GB
LowD38
NVFP4
4
8.4 GB
MediumD38
Q4_K_M
4
9.2 GB
MediumD38
Q5_K_M
5
10.8 GB
HighD38
Q6_K
6
12.3 GB
HighD38
Q8_0
8
16.1 GB
Very HighD39
F16Best for your GPU
16
30.7 GB
MaximumC40

Get started

Copy-paste commands to run Phi 4 reasoning vision 15B on your machine.

Run

lms load hf-jamesburton--phi-4-reasoning-vision-15b-gguf && lms server start

Frequently asked questions

Can AMD Instinct MI250X 128GB run Phi 4 reasoning vision 15B?

Yes, AMD Instinct MI250X 128GB can run Phi 4 reasoning vision 15B with a C grade (Runs well). Expected decode speed: 210.0 tok/s.

How much VRAM does Phi 4 reasoning vision 15B need?

Phi 4 reasoning vision 15B (15B parameters) requires approximately 24.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Phi 4 reasoning vision 15B?

The recommended quantization for Phi 4 reasoning vision 15B is Q4_K_M, which balances quality and memory efficiency.

What speed will Phi 4 reasoning vision 15B run at on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, Phi 4 reasoning vision 15B achieves approximately 210.0 tokens per second decode speed with a time-to-first-token of 922ms using Q4_K_M quantization.

Can AMD Instinct MI250X 128GB run Phi 4 reasoning vision 15B for coding?

For coding workloads, Phi 4 reasoning vision 15B on AMD Instinct MI250X 128GB receives a C grade with 210.0 tok/s and 957K context.

What context window can Phi 4 reasoning vision 15B use on AMD Instinct MI250X 128GB?

On AMD Instinct MI250X 128GB, Phi 4 reasoning vision 15B can safely use up to 957K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for AMD Instinct MI250X 128GBSee all hardware for Phi 4 reasoning vision 15B
Embed this result▼

Paste this snippet into any page to show a live fit card.

<iframe src="https://willitrunai.com/embed/hf-jamesburton--phi-4-reasoning-vision-15b-gguf-on-instinct-mi250x-128gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: