self-hosted/ai
§01·compatibility · /check

Llama 3.1 8B on RX 7900 XTX

Yes — Llama 3.1 8B runs on the RX 7900 XTX (24 GB). Fastest community-measured result: 51.3 tokens/s, with 24 GB peak VRAM.

runsllmactiveamd series24GB VRAM
model
name
Llama 3.1 8B
slug
llama-3-1-8b
vertical
llm
status
active
open detail ↗
gpu
name
RX 7900 XTX
slug
rx-7900-xtx
vram
24 GB
series
amd
open detail ↗
§02·benchmarks
TaskQuantSpeedVRAMWorksConfidenceSourceVerified
llmQ4_K - Medium51.3tokens/s24GBlocalscore.ai· web2026-05-15
§03·common questions
Can you run Llama 3.1 8B on RX 7900 XTX?

Yes — Llama 3.1 8B runs on the RX 7900 XTX (24 GB). Fastest community-measured result: 51.3 tokens/s, with 24 GB peak VRAM.

How much VRAM does Llama 3.1 8B need on RX 7900 XTX?

Measured peak VRAM is 24 GB.

Which quantizations have been tested for Llama 3.1 8B on RX 7900 XTX?

Q4_K - Medium — measured in community benchmarks.

How fast is Llama 3.1 8B on RX 7900 XTX?

Up to 51.3 tokens/s (llm), the fastest community-measured result.

Are there step-by-step instructions for Llama 3.1 8B on RX 7900 XTX?

Yes — a step-by-step recipe documents Llama 3.1 8B on the RX 7900 XTX; see the recipes listed below.

§04·related recipes