Can Phi-4 14B run on NVIDIA L40 48GB?

YES — Runs Great

A81Great

Estimated from fit model

Phi-4 14B needs ~17.3 GB VRAM. NVIDIA L40 48GB has 48.0 GB. With Q4_K_M quantization, expect ~89 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) — 17.3 GB, 89.1 tok/s, Runs well

17.3 GB required48.0 GB available

36% VRAM used

Fit status

Runs well

Decode

89.1 tok/s

TTFT

2173 ms

Safe context

16K

Memory

17.3 GB / 48.0 GB

Memory breakdown

Weights8.5 GB

KV Cache3.1 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsPhi-4 14B on NVIDIA L40 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: 89.1 tok/s decode · 2.2s TTFT (warm) · 223 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	A	Runs well	89.1 tok/s	1186 ms	16K
Coding	A	Runs well	89.1 tok/s	2173 ms	16K
Agentic Coding	A	Runs well	89.1 tok/s	3161 ms	16K
Reasoning	A	Runs well	89.1 tok/s	2569 ms	16K
RAG	A	Runs well	89.1 tok/s	3952 ms	16K

Quantization options

How Phi-4 14B (14B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	A73
Q3_K_S	3	6.9 GB	Low	A74
NVFP4	4	7.8 GB	Medium	A74
Q4_K_M	4	8.5 GB	Medium	A74
Q5_K_M	5	10.1 GB	High	A74
Q6_K	6	11.5 GB	High	A75
Q8_0	8	15.0 GB	Very High	A76
F16Best for your GPU	16	28.7 GB	Maximum	A80

Get started

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

Run

ollama run phi4

Your hardware

More models your NVIDIA L40 48GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	73.4 tok/s
Qwen 3.5 27B	27B	S	30.6 tok/s
Qwen 3.6 27B	27B	S	20.1 tok/s
Qwen 3.6 35B A3B	35B	S	91.6 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	105.4 tok/s

Frequently asked questions

Can NVIDIA L40 48GB run Phi-4 14B?

Yes, NVIDIA L40 48GB can run Phi-4 14B with a A grade (Runs well). Expected decode speed: 89.1 tok/s.

How much VRAM does Phi-4 14B need?

Phi-4 14B (14B parameters) requires approximately 17.3 GB of memory with Q4_K_M quantization.

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

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

What speed will Phi-4 14B run at on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Phi-4 14B achieves approximately 89.1 tokens per second decode speed with a time-to-first-token of 2173ms using Q4_K_M quantization.

Can NVIDIA L40 48GB run Phi-4 14B for coding?

For coding workloads, Phi-4 14B on NVIDIA L40 48GB receives a A grade with 89.1 tok/s and 16K context.

What context window can Phi-4 14B use on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Phi-4 14B can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.

See all results for NVIDIA L40 48GB See all hardware for Phi-4 14B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/phi-4-14b-on-l40-48gb" width="400" height="180" frameborder="0" style="border:none;border-radius:12px;overflow:hidden;" title="Will It Run AI — fit result"></iframe>

Preview:

Workload

Grade

Fit

Decode

TTFT

Context

Chat

Runs well

89.1 tok/s

1186 ms

16K

Coding

Runs well

89.1 tok/s

2173 ms

16K

Agentic Coding

Runs well

89.1 tok/s

3161 ms

16K

Reasoning

Runs well

89.1 tok/s

2569 ms

16K

RAG

Runs well

89.1 tok/s

3952 ms

16K

Quantization options

How Phi-4 14B (14B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	A73
Q3_K_S	3	6.9 GB	Low	A74
NVFP4	4	7.8 GB	Medium	A74
Q4_K_M	4	8.5 GB	Medium	A74
Q5_K_M	5	10.1 GB	High	A74
Q6_K	6	11.5 GB	High	A75
Q8_0	8	15.0 GB	Very High	A76
F16Best for your GPU	16	28.7 GB	Maximum	A80

Model

Params

Grade

Decode

Capabilities

Qwen3-Coder 30B A3B Instruct

30.5B

73.4 tok/s

Qwen 3.5 27B

27B

30.6 tok/s

Qwen 3.6 27B

27B

20.1 tok/s

Qwen 3.6 35B A3B

35B

91.6 tok/s

Qwen3-VL 30B A3B Instruct

30B

105.4 tok/s

Frequently asked questions

Can NVIDIA L40 48GB run Phi-4 14B?

Yes, NVIDIA L40 48GB can run Phi-4 14B with a A grade (Runs well). Expected decode speed: 89.1 tok/s.

How much VRAM does Phi-4 14B need?

Phi-4 14B (14B parameters) requires approximately 17.3 GB of memory with Q4_K_M quantization.

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

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

What speed will Phi-4 14B run at on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Phi-4 14B achieves approximately 89.1 tokens per second decode speed with a time-to-first-token of 2173ms using Q4_K_M quantization.

Can NVIDIA L40 48GB run Phi-4 14B for coding?

For coding workloads, Phi-4 14B on NVIDIA L40 48GB receives a A grade with 89.1 tok/s and 16K context.

What context window can Phi-4 14B use on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Phi-4 14B can safely use up to 16K tokens of context. The model's official context limit is 16K, but available memory constrains the safe maximum.