localLLMriglocal, on your table

estimate

Can I run Qwen2.5 14B on an RX 7900 XTX?

Yes, fully in VRAM (estimate)

Can I run Qwen2.5 14B on an RX 7900 XTX? Yes, fully in VRAM (estimate). About 11.2 GB at Q4_K_M (estimate).

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

Qwen2.5 14B on RX 7900 XTX, formula estimate
QuantContextWeightsKVOverheadTotalUsableFitEst. tok/s
Q4 Q4_K_M8,192 tokens8.8 GB estimate1.6 GB estimate0.8 GB estimate11.2 GB estimate23.4 GB estimatefull37 tok/s estimate
Q5 Q5 (~0.71 bytes/param)8,192 tokens10.4 GB estimate1.6 GB estimate0.8 GB estimate12.8 GB estimate23.4 GB estimatefull32 tok/s estimate
Q8 Q88,192 tokens15.7 GB estimate1.6 GB estimate0.8 GB estimate18.1 GB estimate23.4 GB estimatefull22 tok/s estimate
FP16 FP168,192 tokens29.4 GB estimate1.6 GB estimate0.8 GB estimate31.8 GB estimate23.4 GB estimateno—
Q4, longer context32,768 tokens8.8 GB estimate6.4 GB estimate0.8 GB estimate16.1 GB estimate23.4 GB estimatefull25 tok/s estimate

Formula estimate, not a benchmark. Method →

Cheapest catalog option that fits at Q4

GeForce RTX 3060 12GB, used (median of sold listings), €257, dated 2026-10-16. No buy link.

This hardware

$1,175€1,050

new (out of stock)

price as of 16 Oct 2026

used (3-month median): $1,404€1,254. GPU PRIX. GPU PRIX 3-month median €1,254. 12-month median €1,100. A used Sapphire Nitro+ listing was €982. Not a pcprice.watch sold-listing median.

GPU PRIX

New is out of stock, about €1,050. GPU PRIX showed an XFX Speedster at €1,049 out of stock on 16 Oct 2026. The page's current low of €43 is a cable, not the card. An in-stock ASUS TUF in the table was €3,972, which is not this stored new figure.

Embed this

Qwen2.5 14B on RX 7900 XTX

[![Qwen2.5 14B Q4 on RX 7900 XTX: fits ✓ · est. 37 tok/s (estimate)](https://localllmrig.com/badge/qwen2.5-14b/rx-7900-xtx.svg)](https://localllmrig.com/can-i-run/qwen2.5-14b/rx-7900-xtx?utm_source=badge)

Questions

Can I run Qwen2.5 14B on an RX 7900 XTX?
Yes, fully in VRAM (estimate).
How much memory does Qwen2.5 14B need at Q4?
About 11.2 GB at 8,192 tokens (estimate): 8.8 GB weights, 1.6 GB KV cache, 0.8 GB overhead.
How fast is Qwen2.5 14B on RX 7900 XTX (estimate)?
About 37 tok/s at Q4 (estimate, not a benchmark).
Qwen2.5 14B on RX 7900 XTX (estimate) · localLLMrig