Configure a rig →
Qwen72B params128k contextpopular

Qwen 2.5 72B locally

Qwen 2.5 72B is an open-weight LLM from the Qwen family with 72B parameters. Main use: chat, RAG and general assistance. Detected minimum hardware: Quadro RTX 8000 (48 GB).

Check on my GPU →Hugging Face ↗
Technical facts
Parameters72B
Max context128k
Q4_K_M45.3 GB
Q5_K_M55.3 GB
Q880.5 GB
FP16160.9 GB
FamilyQwen
Last sync2026-05-12

Available quantizations

Q4_K_M
45.3GB

Acceptable. Good compromise when VRAM is limited.

Q5_K_M
55.3GB

Good quality. Sweet spot for size and precision.

Q8
80.5GB

Near-FP16 quality. Comfortable for production.

FP16
160.9GB

Reference precision. Maximum quality, doubled VRAM.

Compatible GPUs

GPUs that can run Qwen 2.5 72B on a single card, ranked by VRAM headroom.

Quadro RTX 8000
NVIDIA
48 GB · Quadro RTX
45.3 / 48 GBtight · Q4
RTX A6000
NVIDIA
48 GB · RTX A (Ampere)
45.3 / 48 GBtight · Q4
RTX 6000 Ada
NVIDIA
48 GB · RTX Ada
45.3 / 48 GBtight · Q4
NVIDIA A40
NVIDIA
48 GB · Ampere DC
45.3 / 48 GBtight · Q4
NVIDIA L40
NVIDIA
48 GB · Lovelace DC
45.3 / 48 GBtight · Q4
NVIDIA L40S
NVIDIA
48 GB · Lovelace DC
45.3 / 48 GBtight · Q4
Radeon Pro W7900
AMD
48 GB · Radeon Pro W
45.3 / 48 GBtight · Q4
Mac Mini M4 Pro (48GB)
Apple
48 GB · Mac Mini
45.3 / 48 GBtight · Q4
MacBook Pro 14 M4 Pro (48GB)
Apple
48 GB · MacBook Pro 14
45.3 / 48 GBtight · Q4
MacBook Pro 14 M4 Max (48GB)
Apple
48 GB · MacBook Pro 14
45.3 / 48 GBtight · Q4
MacBook Pro 16 M3 Max (48GB)
Apple
48 GB · MacBook Pro 16
45.3 / 48 GBtight · Q4
MacBook Pro 16 M4 Pro (48GB)
Apple
48 GB · MacBook Pro 16
45.3 / 48 GBtight · Q4

Recommended multi-GPU rigs

For Qwen 2.5 72B at higher quantization or with more context, a multi-GPU rig gives more headroom.

4× RTX 2060 12GB
NVIDIA
48 GB · RTX 20
45.3 / 48 GBtight · Q4
2× TITAN RTX
NVIDIA
48 GB · RTX 20
45.3 / 48 GBtight · Q4
4× RTX 3060 12GB
NVIDIA
48 GB · RTX 30
45.3 / 48 GBtight · Q4
4× RTX 3080 12GB
NVIDIA
48 GB · RTX 30
45.3 / 48 GBtight · Q4
4× RTX 3080 Ti
NVIDIA
48 GB · RTX 30
45.3 / 48 GBtight · Q4
2× RTX 3090
NVIDIA
48 GB · RTX 30
45.3 / 48 GBtight · Q4
2× RTX 3090 Ti
NVIDIA
48 GB · RTX 30
45.3 / 48 GBtight · Q4
4× RTX 4070
NVIDIA
48 GB · RTX 40
45.3 / 48 GBtight · Q4

Recommended rig

4× RTX 2060 12GB

Qwen 2.5 72B with Ubuntu, vLLM, Open WebUI and the model already downloaded.

Configure →

Similar models

VRAM estimates: parameters x bits/8 plus margin. Real performance varies by engine, context length and batch size.
sync: 2026-05-12