localLLMriglocal, on your table

estimate

Can I run Qwen2.5 32B on an RTX 5090?

Yes, fully in VRAM (estimate)

Can I run Qwen2.5 32B on an RTX 5090? 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 5090, formula estimate
QuantContextWeightsKVOverheadTotalUsableFitEst. tok/s
Q4 Q4_K_M8,192 tokens19.7 GB estimate2.1 GB estimate0.8 GB estimate22.6 GB estimate31.4 GB estimatefull63 tok/s estimate
Q5 Q5 (~0.71 bytes/param)8,192 tokens23.3 GB estimate2.1 GB estimate0.8 GB estimate26.2 GB estimate31.4 GB estimatefull54 tok/s estimate
Q8 Q88,192 tokens35.1 GB estimate2.1 GB estimate0.8 GB estimate38.0 GB estimate31.4 GB estimateno—
FP16 FP168,192 tokens65.6 GB estimate2.1 GB estimate0.8 GB estimate68.5 GB estimate31.4 GB estimateno—
Q4, longer context32,768 tokens19.7 GB estimate8.6 GB estimate0.8 GB estimate29.1 GB estimate31.4 GB estimatefull49 tok/s estimate

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

$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 32B on RTX 5090

[![Qwen2.5 32B Q4 on RTX 5090: fits ✓ · est. 63 tok/s (estimate)](https://localllmrig.com/badge/qwen2.5-32b/rtx-5090.svg)](https://localllmrig.com/can-i-run/qwen2.5-32b/rtx-5090?utm_source=badge)

Questions

Can I run Qwen2.5 32B on an RTX 5090?
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 5090 (estimate)?
About 63 tok/s at Q4 (estimate, not a benchmark).
Qwen2.5 32B on RTX 5090 (estimate) · localLLMrig