Qwen · 32B to 80B

Qwen2.5 VL 72B Instruct

73.41 billion parameters across 80 layers. At four-bit precision the weights alone come to 41.28 GB, before any conversation is loaded. Grouped-query attention keeps the cache small, so long contexts cost less here than on models of the same size.

Vision
Parameters73.41B
Layers80
KV heads8 / 64
Native context125k
Vocabulary152k

Memory needed, by quantisation

At an 8k context window. Quality is our rough ranking of how much the compression costs you: anything at or above Q5 is hard to tell apart from the original in normal use.

Quantisation File size KV cache Total VRAM Quality What it costs you
Q8_0 72.64 GB 2.5 GB 76.24 GB 99% Lossless in practice. Use it when the memory is there.
Q6_K 56.06 GB 2.5 GB 59.66 GB 98% Very close to Q8 for two thirds of the size.
Q5_K_M 48.63 GB 2.5 GB 52.23 GB 96% The quality-first choice when Q6 will not fit.
Q4_K_M 41.28 GB 2.5 GB 44.88 GB 93% The default. Best size-to-quality ratio for local use.
IQ4_XS 36.32 GB 2.5 GB 39.92 GB 91% Importance-matrix 4-bit. Q4_K_S quality, smaller file.
Q3_K_M 33.42 GB 2.5 GB 37.02 GB 86% Degradation starts to show. A way to fit one size up.
IQ3_XXS 26.15 GB 2.5 GB 29.75 GB 79% Aggressive. Only worth it on very large models.

What a longer conversation costs

Same model at Q4_K_M, only the context window changes. This model uses sliding-window attention, so most layers stop growing past 32k tokens and the bill flattens out.

ContextKV cacheTotal VRAMFits in 8 GBFits in 12 GBFits in 24 GB
4k 1.25 GB 43.38 GB no no no
8k 2.5 GB 44.88 GB no no no
16k 5 GB 47.88 GB no no no
32k 10 GB 53.88 GB no no no
64k 10 GB 55.88 GB no no no

The "fits" columns allow for the roughly 0.8 GB Windows keeps for the desktop.

Which hardware runs Qwen2.5 VL 72B Instruct

26 of 118 consumer devices run it at a quantisation worth using, at an 8k context window. Another 23 can load it only by compressing the weights far enough to damage the model, marked with a warning below.

DeviceMemoryVerdictQuantisationUsedSpeed
RTX PRO 6000 Blackwell
NVIDIA
96 GB Runs well Q8_0 76.24 GB 19.6 t/s
RTX 6000 Ada Generation
NVIDIA
48 GB Runs well Q4_K_M 44.88 GB 18 t/s
RTX A6000
NVIDIA
48 GB Runs well Q4_K_M 44.88 GB 14.4 t/s
Apple M1 Ultra 64GB
Apple
64 GB Runs well Q4_K_M 44.58 GB 14.3 t/s
Apple M2 Ultra 64GB
Apple
64 GB Runs well Q4_K_M 44.58 GB 14.3 t/s
Radeon PRO W7900
AMD
48 GB Runs well Q4_K_M 44.88 GB 14.2 t/s
Apple M3 Ultra 96GB
Apple
96 GB Runs well Q6_K 59.36 GB 10.9 t/s
Apple M3 Ultra 256GB
Apple
256 GB Runs well Q6_K 59.36 GB 10.9 t/s
Apple M3 Ultra 512GB
Apple
512 GB Runs well Q6_K 59.36 GB 10.9 t/s
Apple M1 Ultra 128GB
Apple
128 GB Runs well Q6_K 59.36 GB 10.7 t/s
Apple M2 Ultra 128GB
Apple
128 GB Runs well Q6_K 59.36 GB 10.7 t/s
Apple M2 Ultra 192GB
Apple
192 GB Runs well Q6_K 59.36 GB 10.7 t/s
Apple M4 Max 64GB
Apple
64 GB Runs well IQ4_XS 39.62 GB 11 t/s
Apple M4 Max 128GB
Apple
128 GB Runs well IQ4_XS 39.62 GB 11 t/s
GeForce RTX 5090
NVIDIA
32 GB Runs great IQ3_XXS ! 29.75 GB 51.3 t/s
Apple M1 Max 64GB
Apple
64 GB Fits, but slow Q4_K_M 44.58 GB 7.1 t/s
Apple M2 Max 64GB
Apple
64 GB Fits, but slow Q4_K_M 44.58 GB 7.1 t/s
Apple M3 Max 64GB
Apple
64 GB Fits, but slow Q4_K_M 44.58 GB 7.1 t/s
Apple M2 Max 96GB
Apple
96 GB Fits, but slow Q6_K 59.36 GB 5.3 t/s
Apple M3 Max 96GB
Apple
96 GB Fits, but slow Q6_K 59.36 GB 5.3 t/s
Apple M4 Max 48GB
Apple
48 GB Runs well IQ3_XXS ! 29.45 GB 14.9 t/s
Apple M3 Max 128GB
Apple
128 GB Fits, but slow Q8_0 75.94 GB 4.2 t/s
Apple M4 Pro 64GB
Apple
64 GB Fits, but slow Q4_K_M 44.58 GB 4.9 t/s
Apple M3 Max 48GB
Apple
48 GB Runs well IQ3_XXS ! 29.45 GB 10.9 t/s
NVIDIA DGX Spark 128GB
NVIDIA
128 GB Fits, but slow Q8_0 76.24 GB 3 t/s
Ryzen AI Max+ 395 64GB
AMD
64 GB Fits, but slow Q4_K_M 44.88 GB 3.8 t/s
Jetson AGX Orin 64GB
NVIDIA
64 GB Fits, but slow Q4_K_M 44.88 GB 3.8 t/s
Ryzen AI Max+ 395 96GB
AMD
96 GB Fits, but slow Q6_K 59.66 GB 2.8 t/s
Apple M4 Pro 48GB
Apple
48 GB Fits, but slow IQ3_XXS ! 29.45 GB 7.4 t/s
Ryzen AI Max+ 395 128GB
AMD
128 GB Fits, but slow Q8_0 76.24 GB 2.2 t/s
GeForce RTX 4090
NVIDIA
24 GB Runs great IQ2_XXS ! 21.21 GB 41.1 t/s
GeForce RTX 3090 Ti
NVIDIA
24 GB Runs great IQ2_XXS ! 21.21 GB 41.1 t/s
GeForce RTX 3090
NVIDIA
24 GB Runs great IQ2_XXS ! 21.21 GB 38.2 t/s
GeForce RTX 5090 Laptop
NVIDIA
24 GB Runs great IQ2_XXS ! 21.21 GB 36.5 t/s
Radeon RX 7900 XTX
AMD
24 GB Runs great IQ2_XXS ! 21.21 GB 34.4 t/s
RTX A5000
NVIDIA
24 GB Runs great IQ2_XXS ! 21.21 GB 31.3 t/s
Apple M4 Max 36GB
Apple
36 GB Runs well IQ2_XXS ! 20.91 GB 21.2 t/s
Apple M1 Max 32GB
Apple
32 GB Runs well IQ2_XXS ! 20.91 GB 15.5 t/s
Apple M2 Max 32GB
Apple
32 GB Runs well IQ2_XXS ! 20.91 GB 15.5 t/s
Apple M3 Max 36GB
Apple
36 GB Runs well IQ2_XXS ! 20.91 GB 15.5 t/s
Jetson AGX Orin 32GB
NVIDIA
32 GB Fits, but slow IQ2_XXS ! 21.21 GB 8.4 t/s
Ryzen AI Max+ 395 32GB
AMD
32 GB Fits, but slow IQ2_XXS ! 21.21 GB 8.3 t/s
Apple M1 Pro 32GB
Apple
32 GB Fits, but slow IQ2_XXS ! 20.91 GB 7.8 t/s
Apple M2 Pro 32GB
Apple
32 GB Fits, but slow IQ2_XXS ! 20.91 GB 7.8 t/s
Apple M5 32GB
Apple
32 GB Fits, but slow IQ2_XXS ! 20.91 GB 5.9 t/s
Apple M3 Pro 36GB
Apple
36 GB Fits, but slow IQ2_XXS ! 20.91 GB 5.8 t/s
Apple M4 32GB
Apple
32 GB Fits, but slow IQ2_XXS ! 20.91 GB 4.7 t/s
Intel Core Ultra 9 288V 32GB
Intel
32 GB Fits, but slow IQ2_XXS ! 21.21 GB 4.4 t/s
Ryzen AI 9 HX 370 32GB
AMD
32 GB Fits, but slow IQ2_XXS ! 21.21 GB 4.1 t/s
Radeon RX 7900 XT
AMD
20 GB Partial offload 33/80 44.88 GB 1.2 t/s
GeForce RTX 5080
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 5070 Ti
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 5060 Ti 16GB
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 4080 SUPER
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 4080
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 4070 Ti SUPER
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 4060 Ti 16GB
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 4090 Laptop
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
GeForce RTX 5080 Laptop
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s
RTX A4000
NVIDIA
16 GB Partial offload 25/80 44.88 GB 1 t/s

What to buy to run Qwen2.5 VL 72B Instruct

The cheapest hardware that runs it at a quantisation worth using and a speed you would not resent, at an 8k context window.

DevicePriceMemoryRuns it atSpeed
Apple M1 Ultra 64GB
Apple · whole machine
$2,400 64 GB IQ4_XS 16.1 t/s Check price
Apple M1 Ultra 128GB
Apple · whole machine
$3,400 128 GB IQ4_XS 16.1 t/s Check price
RTX A6000
NVIDIA
$3,500 used 48 GB IQ4_XS 16.2 t/s Check price
Apple M3 Ultra 96GB
Apple · whole machine
$3,999 96 GB IQ4_XS 16.5 t/s Check price
Apple M3 Ultra 256GB
Apple · whole machine
$5,599 256 GB IQ4_XS 16.5 t/s Check price
RTX 6000 Ada Generation
NVIDIA
$6,800 48 GB Q4_K_M 18 t/s Check price
RTX PRO 6000 Blackwell
NVIDIA
$8,500 96 GB Q8_0 19.6 t/s Check price
Apple M3 Ultra 512GB
Apple · whole machine
$9,499 512 GB IQ4_XS 16.5 t/s Check price

Indicative prices reviewed 2026-09-01; used prices are marketplace typical. Options that cost more than a cheaper one with no more memory and no more speed are hidden. Price links are Amazon affiliate links. Change the standard, the context window or the budget in the buying tool.

Where it sits in the catalogue

Source: Qwen/Qwen2.5-VL-72B-Instruct on Hugging Face. Downloaded 223k times in the last month. Published 2025-01-27. Architecture figures are read from the repository's own configuration file, so they move when the model does.