willitrun·ai

Can Phi-4-reasoning-plus 14B run on NVIDIA L40S 48GB?

YES — Runs Great

S89Excellent
Estimated from fit model

Phi-4-reasoning-plus 14B needs ~18.0 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~81 tok/s.

Runtime: OllamaCapacity: RoomyBandwidth: HighStack: BasicBottleneck: 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) — 18.0 GB, 80.8 tok/s, Runs well
18.0 GB required48.0 GB available
38% VRAM used

Fit status

Runs well

Decode

80.8 tok/s

TTFT

2396 ms

Safe context

33K

Memory

18.0 GB / 48.0 GB

Memory breakdown

Weights9.0 GB
KV Cache3.1 GB
Runtime1.2 GB
Headroom4.8 GB

See how fast it feels

See how fast it feelsPhi-4-reasoning-plus 14B on NVIDIA L40S 48GB
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: 80.8 tok/s decode · 2.4s TTFT (warm) · 202 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
ChatSRuns well80.8 tok/s1307 ms33K
CodingSRuns well80.8 tok/s2396 ms33K
Agentic CodingSRuns well80.8 tok/s3485 ms33K
ReasoningSRuns well80.8 tok/s2832 ms33K
RAGSRuns well80.8 tok/s4357 ms33K

Inference speed

Phi-4-reasoning-plus 14B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Phi-4-reasoning-plus 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~144 tok/s. Speed is memory-bandwidth bound, so cards that fit the whole model in VRAM run far faster than ones that offload to system RAM.

GPU / MacMemoryQuantSpeed (tok/s)Fits?
NVIDIARTX 5090 32GB
32 GBQ4_K_M143.9Fits
NVIDIARTX 4090 24GB
24 GBQ4_K_M91.8Fits
RX 7900 XTX 24GB
24 GBQ4_K_M82.9Fits
NVIDIARTX 3090 24GB
24 GBQ4_K_M78.5Fits
NVIDIARTX 4080 Super 16GB
16 GBQ4_K_M75.5Tight
Mac Studio M3 Ultra 256GB
256 GBQ4_K_M66.8Fits
Mac Studio M2 Ultra 128GB
128 GBQ4_K_M55.6Fits
Mac Studio M1 Ultra 128GB
128 GBQ4_K_M52.7Fits
MacBook Pro M4 Max 128GB
128 GBQ4_K_M37.6Fits
MacBook Pro M4 Max 64GB
64 GBQ4_K_M37.6Fits
MacBook Pro M3 Max 64GB
64 GBQ4_K_M28.8Fits
MacBook Pro M1 Max 64GB
64 GBQ4_K_M26.4Fits
NVIDIARTX 4070 12GB
12 GBQ4_K_M24.9Heavy offload
MacBook Pro M4 Pro 48GB
48 GBQ4_K_M23.0Fits
NVIDIARTX 3060 12GB
12 GBQ4_K_M14.6Heavy offload
NVIDIARTX 4060 8GB
8 GBQ4_K_M5.5Too big

Estimates for single-stream decoding at Q4_K_M; real tokens/sec varies with prompt length, context, batch size, and runtime build. Prompt processing (prefill) is faster than the decode figures shown here.

Quantization options

How Phi-4-reasoning-plus 14B (14.699999809265137B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

QuantBitsVRAMQualityFit
Q2_K
2
5.7 GB
LowA82
Q3_K_S
3
7.2 GB
LowA82
NVFP4
4
8.2 GB
MediumA82
Q4_K_M
4
9.0 GB
MediumA82
Q5_K_M
5
10.6 GB
HighA83
Q6_K
6
12.1 GB
HighA83
Q8_0
8
15.7 GB
Very HighA84
F16Best for your GPU
16
30.1 GB
MaximumS88

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 NVIDIA L40S 48GB can run

ModelParamsGradeDecodeCapabilities
AlibabaQwen3-Coder 30B A3B Instruct30.5BS101.9 tok/s
AlibabaQwen 3.5 27B27BS44.2 tok/s
AlibabaQwen 3.6 27B27BS44.3 tok/s
AlibabaQwen 3.6 35B A3B35BS91.6 tok/s
AlibabaQwen3-VL 30B A3B Instruct30BS105.4 tok/s

Frequently asked questions

Can NVIDIA L40S 48GB run Phi-4-reasoning-plus 14B?

Yes, NVIDIA L40S 48GB can run Phi-4-reasoning-plus 14B with a S grade (Runs well). Expected decode speed: 80.8 tok/s.

How much VRAM does Phi-4-reasoning-plus 14B need?

Phi-4-reasoning-plus 14B (14.699999809265137B parameters) requires approximately 18.0 GB of memory with Q4_K_M quantization.

What is the best quantization for Phi-4-reasoning-plus 14B?

The recommended quantization for Phi-4-reasoning-plus 14B is Q4_K_M, which balances quality and memory efficiency.

What speed will Phi-4-reasoning-plus 14B run at on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, Phi-4-reasoning-plus 14B achieves approximately 80.8 tokens per second decode speed with a time-to-first-token of 2396ms using Q4_K_M quantization.

Can NVIDIA L40S 48GB run Phi-4-reasoning-plus 14B for coding?

For coding workloads, Phi-4-reasoning-plus 14B on NVIDIA L40S 48GB receives a S grade with 80.8 tok/s and 33K context.

What context window can Phi-4-reasoning-plus 14B use on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, Phi-4-reasoning-plus 14B can safely use up to 33K tokens of context. The model's official context limit is 33K, but available memory constrains the safe maximum.

See all results for NVIDIA L40S 48GBSee all hardware for Phi-4-reasoning-plus 14B
Embed this result▼

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

<iframe src="https://willitrunai.com/embed/phi-4-reasoning-plus-14b-on-l40s-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview: