Can Ministral 3 14B run on Tesla P40 24GB?

YES — Runs Great

S86Excellent

○Estimated from fit model

Ministral 3 14B needs ~15.8 GB VRAM. Tesla P40 24GB has 24.0 GB. With Q4_K_M quantization, expect ~21 tok/s.

Runtime: vLLMCapacity: RoomyBandwidth: LowStack: 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) — 15.8 GB, 20.6 tok/s, Runs well

15.8 GB required24.0 GB available

66% VRAM used

Fit status

Runs well

Decode

20.6 tok/s

TTFT

9418 ms

Safe context

70K

Memory

15.8 GB / 24.0 GB

Memory breakdown

Weights8.5 GB

KV Cache2.4 GB

Runtime2.4 GB

Headroom2.4 GB

See how fast it feels

See how fast it feelsMinistral 3 14B on Tesla P40 24GB
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: 20.6 tok/s decode · 9.4s TTFT (warm) · 51 tok/s prefill

What limits this setup

This setup is broadly balanced for this model.

Older PCIe generation

PCIe 3.0 is workable, but it compounds the penalty when you offload heavily or try to scale across multiple cards.

Best improvement path

Performance by workload

Workload	Grade	Fit	Decode	TTFT	Context
Chat	S	Runs well	20.6 tok/s	5137 ms	70K
Coding	S	Runs well	20.6 tok/s	9418 ms	70K
Agentic Coding	S	Runs well	20.6 tok/s	13698 ms	70K
Reasoning	S	Runs well	20.6 tok/s	11130 ms	70K
RAG	S	Runs well	20.6 tok/s	17123 ms	70K

Quantization options

How Ministral 3 14B (14B params) fits at each quantization level on Tesla P40 24GB (24.0 GB usable).

Quant	Bits	VRAM	Quality	Fit
Q2_K	2	5.5 GB	Low	A81
Q3_K_S	3	6.9 GB	Low	A82
NVFP4	4	7.8 GB	Medium	A82
Q4_K_M	4	8.5 GB	Medium	A83
Q5_K_M	5	10.1 GB	High	A84
Q6_K	6	11.5 GB	High	A85
Q8_0Best for your GPU	8	15.0 GB	Very High	A85
F16	16	28.7 GB	Maximum	F0

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 Tesla P40 24GB can run

Model	Params	Grade	Decode
👁 Alibaba Qwen 3.6 27B	27B	S	10.7 tok/s
👁 Mistral Magistral Small 2507	24B	S	12 tok/s
👁 Mistral Devstral Small 2 24B Instruct	24B	S	12 tok/s
👁 Microsoft Phi-4-reasoning-plus 14B	14.7B	S	19.6 tok/s
👁 Mistral Devstral Small 1.1	24B	S	12 tok/s

Frequently asked questions

See all results for Tesla P40 24GB See all hardware for Ministral 3 14B

URL: https://willitrunai.com/can-run/ministral-3-14b-on-tesla-p40-24gb