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

Llama 3.1 7B on RTX 4090

runsllmactive40 series24GB VRAM
model
name
Llama 3.1 7B
slug
llama-3-1-7b
vertical
llm
status
active
repo
open detail ↗
gpu
name
RTX 4090
slug
rtx-4090
vram
24 GB
series
40
open detail ↗
§02·benchmarks
TaskQuantSpeedVRAMWorksConfidenceSourceVerified
llmQ4_K_M135tok/s24GBmustafa.net· web2026-05-15