localLLMriglocal, on your table

estimate

Can I run Llama 3.1 8B on an RX 7900 XTX?

Yes, fully in VRAM (estimate)

Can I run Llama 3.1 8B on an RX 7900 XTX? Yes, fully in VRAM (estimate). About 6.7 GB at Q4_K_M (estimate).

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

Llama 3.1 8B on RX 7900 XTX, formula estimate
QuantContextWeightsKVOverheadTotalUsableFitEst. tok/s
Q4 Q4_K_M8,192 tokens4.8 GB estimate1.1 GB estimate0.8 GB estimate6.7 GB estimate23.4 GB estimatefull64 tok/s estimate
Q5 Q5 (~0.71 bytes/param)8,192 tokens5.7 GB estimate1.1 GB estimate0.8 GB estimate7.6 GB estimate23.4 GB estimatefull56 tok/s estimate
Q8 Q88,192 tokens8.6 GB estimate1.1 GB estimate0.8 GB estimate10.5 GB estimate23.4 GB estimatefull39 tok/s estimate
FP16 FP168,192 tokens16.1 GB estimate1.1 GB estimate0.8 GB estimate17.9 GB estimate23.4 GB estimatefull22 tok/s estimate
Q4, longer context32,768 tokens4.8 GB estimate4.3 GB estimate0.8 GB estimate9.9 GB estimate23.4 GB estimatefull42 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

Llama 3.1 8B on RX 7900 XTX

[![Llama 3.1 8B Q4 on RX 7900 XTX: fits ✓ · est. 64 tok/s (estimate)](https://localllmrig.com/badge/llama-3.1-8b/rx-7900-xtx.svg)](https://localllmrig.com/can-i-run/llama-3.1-8b/rx-7900-xtx?utm_source=badge)

Questions

Can I run Llama 3.1 8B on an RX 7900 XTX?
Yes, fully in VRAM (estimate).
How much memory does Llama 3.1 8B need at Q4?
About 6.7 GB at 8,192 tokens (estimate): 4.8 GB weights, 1.1 GB KV cache, 0.8 GB overhead.
How fast is Llama 3.1 8B on RX 7900 XTX (estimate)?
About 64 tok/s at Q4 (estimate, not a benchmark).
Llama 3.1 8B on RX 7900 XTX (estimate) · localLLMrig