Can I Run Qwen 2.5 Family on NVIDIA L40S?

Superseded model. Qwen 2.5 Family has been superseded by Qwen 3. This page is kept for reference; the newer family is a better starting point. View Qwen 3 →

Autor: Jakub Rusinowski · Ostatnia aktualizacja: 21 lipca 2026

Yes, but it's tight — Qwen 2.5 72B Instruct at Q4_K_M needs 43.47 GB of the NVIDIA L40S's 48 GB, leaving only ~4.5 GB, ~17 tok/s (est.) with room for up to 8K context.

Buy This HardwareNVIDIA L40S 48GB — 48 GB VRAM · 350 W board powerDeploy in the Cloud NowNVIDIA L40S on RunPod — from $0.86/hr · rate checked 2026-08

or compare on Vast.ai

As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.

Ujawnienie afiliacyjne: Niektóre odnośniki na tej stronie to linki afiliacyjne — jeśli dokonasz zakupu za ich pośrednictwem, LLM Configurator może otrzymać prowizję bez dodatkowych kosztów dla Ciebie. Jako uczestnik programu Amazon Associates, LLM Configurator zarabia na kwalifikujących się zakupach.

NVIDIA L40S 48GB
48 GB VRAM · 350 W board power
Ceny w 2026 są niestabilne — sprawdź aktualną ofertę.
Sprawdź cenę na Amazon

NVIDIA L40S Specs

VRAM48 GB
Memory Bandwidth864 GB/s

Qwen 2.5 72B Instruct on the NVIDIA L40S: VRAM by quantization

QuantVRAM neededFits 48 GB?Max context
F16146.1 GB✗ No
Q8_078.6 GB✗ No
Q6_K61.2 GB✗ No
Q5_K_M53.2 GB✗ No
Q4_K_M45.6 GB✓ Yes8K
Q3_K_M32.8 GB✓ Yes32K
Q2_K25.8 GB✓ Yes64K

VRAM needed assumes a 4K-token context with an f16 KV cache; “Max context” is the largest window that still fits in 48 GB. Figures are estimates from parameter count, quantization and memory bandwidth — the analyzer lets you tune KV-cache quant and context.

Qwen 2.5 Family Sizes That Fit the NVIDIA L40S

Qwen 2.5 72B InstructQ4_K_M · 43.47 GB · ~17 tok/s (est.)
Qwen 2.5 Coder 32BQ4_K_M · 19.32 GB · ~36 tok/s (est.)
Qwen 2.5 14B InstructQ4_K_M · 8.4525 GB · ~72 tok/s (est.)
Qwen 2.5 7B InstructQ4_K_M · 4.5885 GB · ~121 tok/s (est.)
Buy vs. rent Qwen 2.5 Family
Buy the GPU
~$7,499
NVIDIA L40S · MSRP
Rent by the hour
from $0.77/hr
A100 (80 GB) class

At 2 hrs/day, buying (~$7,499) beats renting at $0.77/hr after about 13.5 years.

Affiliate links — we may earn a commission if you sign up, at no extra cost to you.

Vast.ai $0.77/hr · typical low · varies
Rent on Vast.ai →
RunPod $1.39/hr
Rent on RunPod →

Cloud rates verified 2026-07 — estimates, and marketplace prices vary. Buying price is GPU MSRP only, not a full PC.

FAQ

Is the NVIDIA L40S enough to run Qwen 2.5 Family locally?

Yes, but it's tight — Qwen 2.5 72B Instruct at Q4_K_M needs 43.47 GB of the NVIDIA L40S's 48 GB, leaving only ~4.5 GB, ~17 tok/s (est.) with room for up to 8K context.

What's the best Qwen 2.5 Family size for the NVIDIA L40S?

Qwen 2.5 72B Instruct at Q4_K_M quantization (43.47 GB), estimated ~17 tokens/sec, up to 8K context.

Every Qwen 2.5 Family size on the NVIDIA L40S

SizeVRAMVerdictSpeed
Qwen 2.5 72B Instruct43.5 GBRuns~17 tok/s
Qwen 2.5 Coder 32B19.3 GBRuns~36 tok/s
Qwen 2.5 14B Instruct8.5 GBRuns~72 tok/s
Qwen 2.5 7B Instruct4.6 GBRuns~121 tok/s

Qwen 2.5 Family on Other GPUs

Popular Models on the NVIDIA L40S

VRAM Tier

Troubleshooting

Buying Guide

← Can I Run It? | Qwen 2.5 Family Model Page | NVIDIA L40S GPU Page | Check Your Hardware