How much memory does Qwen2.5 72B need at Q4?

About 47.1 GB at 8,192 tokens (estimate): 43.6 GB weights, 2.7 GB KV cache, 0.8 GB overhead.

How fast is Qwen2.5 72B on RTX 5090 (estimate)?

No tokens-per-second estimate. The Q4 fit is not full and not offload, so this page leaves speed blank.

estimate

Can I run Qwen2.5 72B on an RTX 5090?

No: needs ~47.1 GB, this card has ~31.4 GB usable (estimate)

Can I run Qwen2.5 72B on an RTX 5090? No: needs ~47.1 GB, this card has ~31.4 GB usable (estimate). About 47.1 GB at Q4_K_M (estimate).

Updated 2026-10-16. The later of the hardware price date and the formula date.

Qwen2.5 72B on RTX 5090, formula estimate
Quant	Context	Weights	KV	Overhead	Total	Usable	Fit	Est. tok/s
Q4 Q4_K_M	8,192 tokens	43.6 GB estimate	2.7 GB estimate	0.8 GB estimate	47.1 GB estimate	31.4 GB estimate	no	—
Q5 Q5 (~0.71 bytes/param)	8,192 tokens	51.6 GB estimate	2.7 GB estimate	0.8 GB estimate	55.1 GB estimate	31.4 GB estimate	no	—
Q8 Q8	8,192 tokens	77.8 GB estimate	2.7 GB estimate	0.8 GB estimate	81.3 GB estimate	31.4 GB estimate	no	—
FP16 FP16	8,192 tokens	145.4 GB estimate	2.7 GB estimate	0.8 GB estimate	148.9 GB estimate	31.4 GB estimate	no	—
Q4, longer context	32,768 tokens	43.6 GB estimate	10.7 GB estimate	0.8 GB estimate	55.2 GB estimate	31.4 GB estimate	no	—

Formula estimate, not a benchmark. Method →

Cheapest catalog option that fits at Q4

Mac mini M4 Pro 64GB, catalog price, €1,890, dated 2026-10-16. No buy link.

This hardware

$7,052€6,299

new (lowest in-stock EU)

price as of 16 Oct 2026

PriceSquirrel

Cheapest in-stock listing on 16 Oct 2026: €6,299, ASUS ROG Astral GeForce RTX 5090 32GB OC White at Proshop (FI). MSI Gaming Trio OC at Compumsa (BE) was €6,571 and out of stock. A 16 Oct 2026 fact-check notes BE/NL/DE about €7,900–€8,800. No used median was recorded. NVIDIA (Jeff Fisher, 16 Oct 2026) denies a production halt; supply is tight and some retailers have delisted the card.

Embed this

Qwen2.5 72B on RTX 5090

[![Qwen2.5 72B Q4 on RTX 5090: ✗ · needs 47.1 GB (estimate)](https://localllmrig.com/badge/qwen2.5-72b/rtx-5090.svg)](https://localllmrig.com/can-i-run/qwen2.5-72b/rtx-5090?utm_source=badge)

Questions

Can I run Qwen2.5 72B on an RTX 5090?: No: needs ~47.1 GB, this card has ~31.4 GB usable (estimate).
How much memory does Qwen2.5 72B need at Q4?: About 47.1 GB at 8,192 tokens (estimate): 43.6 GB weights, 2.7 GB KV cache, 0.8 GB overhead.
How fast is Qwen2.5 72B on RTX 5090 (estimate)?: No tokens-per-second estimate. The Q4 fit is not full and not offload, so this page leaves speed blank.