Can Llama 3.3 70B run on NVIDIA L40 48GB?

BARELY — Tight on Memory

A71Great

Estimated from fit model

Llama 3.3 70B needs ~53.6 GB VRAM. NVIDIA L40 48GB has 48.0 GB. With Q4_K_M quantization, expect ~9 tok/s.

Runtime: OllamaCapacity: OffloadBandwidth: HighStack: BasicBottleneck: Host offload

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) — 53.6 GB, 10.2 tok/s, Very compromised (needs ~4.4 GB host RAM)

53.6 GB required48.0 GB available

112% VRAM needed

5.6 GB over capacity — needs offload or smaller quantization

Fit status

Very compromised (needs ~4.4 GB host RAM)

Decode

10.2 tok/s

TTFT

18959 ms

Safe context

Memory

53.6 GB / 48.0 GB

Offload

10%

Memory breakdown

Weights42.7 GB

KV Cache4.9 GB

Runtime1.2 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsLlama 3.3 70B 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: 10.2 tok/s decode · 19.0s TTFT (warm) · 26 tok/s prefill

What limits this setup

It fits through host-memory offload, and offload is the main reason performance drops.

CPU or host-memory offload is active

About 10% of the working set spills out of accelerator memory, which usually hurts latency and sustained decode throughput.

Very little memory headroom

You can run the model, but there is not much room left for longer context, bigger batches, extra apps, or future model updates.

Best improvement path

Remove offload with more accelerator memory

Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

Buy headroom, not only minimum fit

A slightly larger memory tier gives you safer context growth and makes the recommendation more future-proof.

Increase host RAM if you keep offloading

This setup may need roughly {ram} GB of extra host RAM just for the offloaded portion, before OS and other tools.

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	A	Runs with offload (needs ~2.6 GB host RAM)	11.3 tok/s	9374 ms	4K
Coding	A	Very compromised	9.4 tok/s	20618 ms	4K
Agentic Coding	F	Too heavy	8.5 tok/s	33134 ms	4K
Reasoning	A	Very compromised (needs ~4.4 GB host RAM)	10.2 tok/s	22406 ms	4K
RAG	F	Too heavy	8.5 tok/s	41418 ms	4K

Quantization options

How Llama 3.3 70B (70B params) fits at each quantization level on NVIDIA L40 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	27.3 GB	Low	A82
Q3_K_SBest for your GPU	3	34.3 GB	Low	A82
NVFP4	4	39.2 GB	Medium	F0
Q4_K_M	4	42.7 GB	Medium	F0
Q5_K_M	5	50.4 GB	High	F0
Q6_K	6	57.4 GB	High	F0
Q8_0	8	74.9 GB	Very High	F0
F16	16	143.5 GB	Maximum	F0

Get started

Copy-paste commands to run Llama 3.3 70B on your machine.

Run

ollama run llama3.3

Your hardware

More models your NVIDIA L40 48GB can run

Model	Params	Grade	Decode	Capabilities
Qwen 2.5 VL 72B	72B	A	9.5 tok/s
Qwen3-Coder-Next	80B	A	24.4 tok/s

Frequently asked questions

Can NVIDIA L40 48GB run Llama 3.3 70B?

Yes, NVIDIA L40 48GB can run Llama 3.3 70B with a A grade (Very compromised). Expected decode speed: 9.4 tok/s.

How much VRAM does Llama 3.3 70B need?

Llama 3.3 70B (70B parameters) requires approximately 53.6 GB of memory with Q4_K_M quantization.

What is the best quantization for Llama 3.3 70B?

The recommended quantization for Llama 3.3 70B is Q4_K_M, which balances quality and memory efficiency.

What speed will Llama 3.3 70B run at on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Llama 3.3 70B achieves approximately 9.4 tokens per second decode speed with a time-to-first-token of 20618ms using Q4_K_M quantization.

Can NVIDIA L40 48GB run Llama 3.3 70B for coding?

For coding workloads, Llama 3.3 70B on NVIDIA L40 48GB receives a A grade with 9.4 tok/s and 4K context.

What context window can Llama 3.3 70B use on NVIDIA L40 48GB?

On NVIDIA L40 48GB, Llama 3.3 70B can safely use up to 4K tokens of context. The model's official context limit is 128K, but available memory constrains the safe maximum.

What should I upgrade first if Llama 3.3 70B feels slow on NVIDIA L40 48GB?

Remove offload with more accelerator memory. Prioritize a GPU or unified-memory tier that fits the whole model natively. Removing offload usually helps more than small compute gains.

See all results for NVIDIA L40 48GB See all hardware for Llama 3.3 70B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/llama-3.3-70b-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: