localLLMriglocal, on your table

estimate

Can I run Llama 3.3 70B on an RX 7900 XTX?

No: needs ~45.8 GB, this card has ~23.4 GB usable (estimate)

Can I run Llama 3.3 70B on an RX 7900 XTX? No: needs ~45.8 GB, this card has ~23.4 GB usable (estimate). About 45.8 GB at Q4_K_M (estimate).

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

Llama 3.3 70B on RX 7900 XTX, formula estimate
QuantContextWeightsKVOverheadTotalUsableFitEst. tok/s
Q4 Q4_K_M8,192 tokens42.4 GB estimate2.7 GB estimate0.8 GB estimate45.8 GB estimate23.4 GB estimateno—
Q5 Q5 (~0.71 bytes/param)8,192 tokens50.1 GB estimate2.7 GB estimate0.8 GB estimate53.6 GB estimate23.4 GB estimateno—
Q8 Q88,192 tokens75.5 GB estimate2.7 GB estimate0.8 GB estimate79.0 GB estimate23.4 GB estimateno—
FP16 FP168,192 tokens141.2 GB estimate2.7 GB estimate0.8 GB estimate144.7 GB estimate23.4 GB estimateno—
Q4, longer context32,768 tokens42.4 GB estimate10.7 GB estimate0.8 GB estimate53.9 GB estimate23.4 GB estimateno—

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

$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 3.3 70B on RX 7900 XTX

[![Llama 3.3 70B Q4 on RX 7900 XTX: ✗ · needs 45.8 GB (estimate)](https://localllmrig.com/badge/llama-3.3-70b/rx-7900-xtx.svg)](https://localllmrig.com/can-i-run/llama-3.3-70b/rx-7900-xtx?utm_source=badge)

Questions

Can I run Llama 3.3 70B on an RX 7900 XTX?
No: needs ~45.8 GB, this card has ~23.4 GB usable (estimate).
How much memory does Llama 3.3 70B need at Q4?
About 45.8 GB at 8,192 tokens (estimate): 42.4 GB weights, 2.7 GB KV cache, 0.8 GB overhead.
How fast is Llama 3.3 70B on RX 7900 XTX (estimate)?
No tokens-per-second estimate. The Q4 fit is not full and not offload, so this page leaves speed blank.
Llama 3.3 70B on RX 7900 XTX (estimate) · localLLMrig