localLLMriglocal, on your table

estimate

Can I run Qwen2.5 32B on an RTX 4090?

Yes, fully in VRAM (estimate)

Can I run Qwen2.5 32B on an RTX 4090? Yes, fully in VRAM (estimate). About 22.6 GB at Q4_K_M (estimate).

Updated . The later of the hardware price date and the formula date.

Qwen2.5 32B on RTX 4090, formula estimate
QuantContextWeightsKVOverheadTotalUsableFitEst. tok/s
Q4 Q4_K_M8,192 tokens19.7 GB estimate2.1 GB estimate0.8 GB estimate22.6 GB estimate23.4 GB estimatefull36 tok/s estimate
Q5 Q5 (~0.71 bytes/param)8,192 tokens23.3 GB estimate2.1 GB estimate0.8 GB estimate26.2 GB estimate23.4 GB estimateno—
Q8 Q88,192 tokens35.1 GB estimate2.1 GB estimate0.8 GB estimate38.0 GB estimate23.4 GB estimateno—
FP16 FP168,192 tokens65.6 GB estimate2.1 GB estimate0.8 GB estimate68.5 GB estimate23.4 GB estimateno—
Q4, longer context32,768 tokens19.7 GB estimate8.6 GB estimate0.8 GB estimate29.1 GB estimate23.4 GB estimateno—

Formula estimate, not a benchmark. Method →

Cheapest catalog option that fits at Q4

Radeon RX 7900 XTX 24GB, new (out of stock), €1,050, dated 2026-10-16. No buy link.

This hardware

$2,446€2,185

used (median of sold listings)

price as of 16 Oct 2026

new (lowest in-stock EU): $4,243€3,790. GPU PRIX. Current low €3,790, MSI Gaming X Slim, Belgium. Page last updated 15 Oct 2026, checked 16 Oct 2026. In-stock boards in that table start at €3,990.

pcprice.watch

Used median €2,185, typical €2,074–€2,290, 111 sales, updated 16 Oct 2026. Not an EU retail listing.

Embed this

Qwen2.5 32B on RTX 4090

[![Qwen2.5 32B Q4 on RTX 4090: fits ✓ · est. 36 tok/s (estimate)](https://localllmrig.com/badge/qwen2.5-32b/rtx-4090.svg)](https://localllmrig.com/can-i-run/qwen2.5-32b/rtx-4090?utm_source=badge)

Questions

Can I run Qwen2.5 32B on an RTX 4090?
Yes, fully in VRAM (estimate).
How much memory does Qwen2.5 32B need at Q4?
About 22.6 GB at 8,192 tokens (estimate): 19.7 GB weights, 2.1 GB KV cache, 0.8 GB overhead.
How fast is Qwen2.5 32B on RTX 4090 (estimate)?
About 36 tok/s at Q4 (estimate, not a benchmark).
Qwen2.5 32B on RTX 4090 (estimate) · localLLMrig