Can StableLM 2 12B run on NVIDIA L40S 48GB?

YES — Runs Great

C53Usable

○Estimated from fit model

StableLM 2 12B needs ~26.5 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q5_K_M quantization, expect ~72 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

Q5_K_M (High quality) — 26.5 GB, 71.8 tok/s, Runs well

26.5 GB required48.0 GB available

55% VRAM used

Fit status

Runs well

Decode

71.8 tok/s

TTFT

2695 ms

Safe context

Memory

26.5 GB / 48.0 GB

Memory breakdown

Weights8.6 GB

KV Cache12.2 GB

Runtime0.9 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsStableLM 2 12B on NVIDIA L40S 48GB
1st promptCold start — includes initialization
>What is local AI inference?
Local AI inference means running an AI language model directly on your own hardware — your laptop, desktop, or server — instead of sending requests to a remote cloud API.

When you run inference locally the model weights are loaded into your GPU or unified memory. Each token you generate requires reading those weights from memory, so memory bandwidth is the main bottleneck for decode speed.

Key benefits of running locally:
 - Full privacy: your prompts never leave your machine
 - No per-token cost or rate limits
 - Works offline once the model is downloaded
 - Latency depends only on your hardware
2nd promptWarm — model ready, no init overhead
>How much VRAM do I need?
It depends on the model size and quantization level. A rough rule of thumb:

 Model size Q4 (4-bit) Q8 (8-bit) FP16
 7B params ~4.3 GB ~7.5 GB ~14 GB
 13B params ~7.9 GB ~13.9 GB ~26 GB
 70B params ~42.7 GB ~74.9 GB ~140 GB

Most people use 4-bit quantization (Q4_K_M) which gives 90-95% of full quality at a fraction of the memory. A 24 GB GPU can comfortably run most 7B-13B models.
Estimated: 71.8 tok/s decode · 2.7s TTFT (warm) · 180 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	71.8 tok/s	1470 ms	4K
Coding	C	Runs well	71.8 tok/s	2695 ms	4K
Agentic Coding	B	Runs well	71.8 tok/s	3920 ms	4K
Reasoning	C	Runs well	71.8 tok/s	3185 ms	4K
RAG	B	Runs well	71.8 tok/s	4900 ms	4K

Quantization options

How StableLM 2 12B (12B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	4.7 GB	Low	C41
Q3_K_S	3	5.9 GB	Low	C42
NVFP4	4	6.7 GB	Medium	C42
Q4_K_M	4	7.3 GB	Medium	C42
Q5_K_M	5	8.6 GB	High	C42
Q6_K	6	9.8 GB	High	C43
Q8_0	8	12.8 GB	Very High	C43
F16Best for your GPU	16	24.6 GB	Maximum	C47

Get started

Copy-paste commands to run StableLM 2 12B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
 --hf-repo "stabilityai/stablelm-2-12b-chat" \
 --hf-file "stablelm-2-12b-chat-Q5_K_M.gguf" \
 -c 4096 -ngl 99

Frequently asked questions

See all results for NVIDIA L40S 48GB See all hardware for StableLM 2 12B

URL: https://willitrunai.com/can-run/stablelm-2-12b-on-l40s-48gb

⇱ StableLM 2 12B on NVIDIA L40S 48GB? YES