Can Ministral 3 14B run on NVIDIA L40S 48GB?

YES — Runs Great

A84Great

Estimated from fit model

Ministral 3 14B needs ~18.2 GB VRAM. NVIDIA L40S 48GB has 48.0 GB. With Q4_K_M quantization, expect ~68 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: HighStack: OptimizedBottleneck: 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) — 18.2 GB, 67.9 tok/s, Runs well

18.2 GB required48.0 GB available

38% VRAM used

Fit status

Runs well

Decode

67.9 tok/s

TTFT

2853 ms

Safe context

211K

Memory

18.2 GB / 48.0 GB

Memory breakdown

Weights8.5 GB

KV Cache2.4 GB

Runtime2.4 GB

Headroom4.8 GB

See how fast it feels

See how fast it feelsMinistral 3 14B 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: 67.9 tok/s decode · 2.9s TTFT (warm) · 170 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	67.9 tok/s	1556 ms	211K
Coding	A	Runs well	67.9 tok/s	2853 ms	211K
Agentic Coding	S	Runs well	67.9 tok/s	4149 ms	211K
Reasoning	A	Runs well	67.9 tok/s	3371 ms	211K
RAG	S	Runs well	67.9 tok/s	5187 ms	211K

Inference speed

Ministral 3 14B inference speed — tokens per second by GPU & Mac

Estimated decode speed (tokens/sec) for Ministral 3 14B at Q4_K_M across popular GPUs and Apple Silicon, using the fastest local runtime per device. Fastest is RTX 5090 32GB at ~121 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 / Mac	Memory	Quant	Speed (tok/s)	Fits?
RTX 5090 32GB	32 GB	Q4_K_M	120.9	Fits
RX 7900 XTX 24GB	24 GB	Q4_K_M	87.0	Fits
RTX 4090 24GB	24 GB	Q4_K_M	77.1	Fits
Mac Studio M3 Ultra 256GB	256 GB	Q4_K_M	70.1	Fits
RTX 3090 24GB	24 GB	Q4_K_M	66.0	Fits
RTX 4080 Super 16GB	16 GB	Q4_K_M	61.5	Tight
Mac Studio M2 Ultra 128GB	128 GB	Q4_K_M	58.4	Fits
Mac Studio M1 Ultra 128GB	128 GB	Q4_K_M	55.4	Fits
MacBook Pro M4 Max 128GB	128 GB	Q4_K_M	38.1	Fits
MacBook Pro M4 Max 64GB	64 GB	Q4_K_M	38.1	Fits
MacBook Pro M3 Max 64GB	64 GB	Q4_K_M	30.2	Fits
MacBook Pro M1 Max 64GB	64 GB	Q4_K_M	27.7	Fits
RTX 4070 12GB	12 GB	Q4_K_M	25.9	Heavy offload
MacBook Pro M4 Pro 48GB	48 GB	Q4_K_M	23.3	Fits
RTX 3060 12GB	12 GB	Q4_K_M	16.3	Heavy offload
RTX 4060 8GB	8 GB	Q4_K_M	4.5	Too 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 Ministral 3 14B (14B params) fits at each quantization level on NVIDIA L40S 48GB (48.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	A77
Q3_K_S	3	6.9 GB	Low	A77
NVFP4	4	7.8 GB	Medium	A77
Q4_K_M	4	8.5 GB	Medium	A77
Q5_K_M	5	10.1 GB	High	A78
Q6_K	6	11.5 GB	High	A78
Q8_0	8	15.0 GB	Very High	A79
F16Best for your GPU	16	28.7 GB	Maximum	A83

Get started

Copy-paste commands to run Ministral 3 14B on your machine.

Run

docker run --rm -it ghcr.io/ggerganov/llama.cpp:full \
  --hf-repo "mistralai/Ministral-3-14B-Instruct-2512" \
  --hf-file "Ministral-3-14B-Instruct-2512-Q4_K_M.gguf" \
  -c 4096 -ngl 99

Your hardware

More models your NVIDIA L40S 48GB can run

Model	Params	Grade	Decode
Qwen3-Coder 30B A3B Instruct	30.5B	S	77.4 tok/s
Qwen 3.5 27B	27B	S	35.4 tok/s
Qwen 3.6 27B	27B	S	35.5 tok/s
Qwen 3.6 35B A3B	35B	S	65.1 tok/s
Qwen3-VL 30B A3B Instruct	30B	S	80.1 tok/s

Frequently asked questions

Can NVIDIA L40S 48GB run Ministral 3 14B?

Yes, NVIDIA L40S 48GB can run Ministral 3 14B with a A grade (Runs well). Expected decode speed: 67.9 tok/s.

How much VRAM does Ministral 3 14B need?

Ministral 3 14B (14B parameters) requires approximately 18.2 GB of memory with Q4_K_M quantization.

What is the best quantization for Ministral 3 14B?

The recommended quantization for Ministral 3 14B is Q4_K_M, which balances quality and memory efficiency.

What speed will Ministral 3 14B run at on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, Ministral 3 14B achieves approximately 67.9 tokens per second decode speed with a time-to-first-token of 2853ms using Q4_K_M quantization.

Can NVIDIA L40S 48GB run Ministral 3 14B for coding?

For coding workloads, Ministral 3 14B on NVIDIA L40S 48GB receives a A grade with 67.9 tok/s and 211K context.

What context window can Ministral 3 14B use on NVIDIA L40S 48GB?

On NVIDIA L40S 48GB, Ministral 3 14B can safely use up to 211K tokens of context. The model's official context limit is 262K, but available memory constrains the safe maximum.

See all results for NVIDIA L40S 48GB See all hardware for Ministral 3 14B

Embed this result▼

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

<iframe src="https://willitrunai.com/embed/ministral-3-14b-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: