models/qwen-qwen2.5-72b-instruct

Qwen2.5 72B

Sources arena · Confidence C

params

72B

dense

bench sources

single

context

—

max tokens

license

Qwen

see source

▸Model meta

▸Benchmark breakdown

▸Hardware fit matrix

by gpu tier	Q2_K 27.0 GB	Q4_K_M 36.0 GB	Q5_K_M 45.0 GB	Q6_K 54.0 GB	Q8_0 72.0 GB
8 GB tier rtx 3050 · 4060
12 GB tier rtx 3060 · 4070
16 GB tier rtx 4080 · 4060 ti 16g
24 GB tier rtx 3090 · 4090
32 GB tier rtx 5090 · m3 max	OK 62 t/s
48 GB tier a6000 · m3 max 64	GREAT 20 t/s	GREAT 15 t/s
80 GB tier h100 · m3 ultra 128	GREAT 68 t/s	GREAT 51 t/s	GREAT 41 t/s	GREAT 34 t/s	TIGHT 26 t/s

full fit · production speed tight fit · usabledoesn't fit

Get personalized ranking

Tell us your machine — we'll tell you if this is actually your best pick, or what's better.