Can Phi 4 reasoning vision 15B run on RTX PRO 4000 Blackwell 24GB?

YES — Runs Great

C53Usable

Estimated from fit model

Phi 4 reasoning vision 15B needs ~14.5 GB VRAM. RTX PRO 4000 Blackwell 24GB has 24.0 GB. With Q4_K_M quantization, expect ~62 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: MediumStack: BasicBottleneck: 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) — 14.5 GB, 61.7 tok/s, Runs well

14.5 GB required24.0 GB available

60% VRAM used

Fit status

Runs well

Decode

61.7 tok/s

TTFT

3138 ms

Safe context

102K

Memory

14.5 GB / 24.0 GB

Memory breakdown

Weights9.2 GB

KV Cache1.8 GB

Runtime1.2 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsPhi 4 reasoning vision 15B on RTX PRO 4000 Blackwell 24GB
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: 61.7 tok/s decode · 3.1s TTFT (warm) · 154 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	C	Runs well	61.7 tok/s	1712 ms	102K
Coding	C	Runs well	61.7 tok/s	3138 ms	102K
Agentic Coding	B	Runs well	61.7 tok/s	4565 ms	102K
Reasoning	C	Runs well	61.7 tok/s	3709 ms	102K
RAG	B	Runs well	61.7 tok/s	5706 ms	102K

Quantization options

How Phi 4 reasoning vision 15B (15B params) fits at each quantization level on RTX PRO 4000 Blackwell 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.9 GB	Low	C46
Q3_K_S	3	7.4 GB	Low	C47
NVFP4	4	8.4 GB	Medium	C47
Q4_K_M	4	9.2 GB	Medium	C48
Q5_K_M	5	10.8 GB	High	C49
Q6_K	6	12.3 GB	High	C50
Q8_0Best for your GPU	8	16.1 GB	Very High	C50
F16	16	30.7 GB	Maximum	F0

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 RTX PRO 4000 Blackwell 24GB run Phi 4 reasoning vision 15B?

Yes, RTX PRO 4000 Blackwell 24GB can run Phi 4 reasoning vision 15B with a C grade (Runs well). Expected decode speed: 61.7 tok/s.

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

Phi 4 reasoning vision 15B (15B parameters) requires approximately 14.5 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 RTX PRO 4000 Blackwell 24GB?

On RTX PRO 4000 Blackwell 24GB, Phi 4 reasoning vision 15B achieves approximately 61.7 tokens per second decode speed with a time-to-first-token of 3138ms using Q4_K_M quantization.

Can RTX PRO 4000 Blackwell 24GB run Phi 4 reasoning vision 15B for coding?

For coding workloads, Phi 4 reasoning vision 15B on RTX PRO 4000 Blackwell 24GB receives a C grade with 61.7 tok/s and 102K context.

What context window can Phi 4 reasoning vision 15B use on RTX PRO 4000 Blackwell 24GB?

On RTX PRO 4000 Blackwell 24GB, Phi 4 reasoning vision 15B can safely use up to 102K tokens of context. The model's official context limit is —, but available memory constrains the safe maximum.

See all results for RTX PRO 4000 Blackwell 24GB See 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-rtx-pro-4000-blackwell-24gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: