Best home rig for Llama 3 8B
Older model. For current picks see 2025–2026 models.
Real, measured generation speeds for Llama 3 8B on home hardware, fastest first. Different quants/engines aren't directly comparable.
| Build | Quant | Engine | tok/s | Cost | |
|---|---|---|---|---|---|
| MacBook Pro M3 Max 40-core GPU, 64 GB | Q4_K_M | llama.cpp | 50.74 | source | |
| MacBook Pro M1 Max 32-core GPU, 64 GB | Q4_K_M | llama.cpp | 34.49 | source |
SPONSOR
Your brand here. One sponsor slot on this page, shown to people choosing AI hardware. Sponsor RigBase →
Your brand here. One sponsor slot on this page, shown to people choosing AI hardware. Sponsor RigBase →
Rent before you buy: try this model on a cloud GPU for a few dollars first: RunPod
FAQ
What is the fastest measured hardware for Llama 3 8B?
Apple M3 Max: 50.74 tok/s generation (llama.cpp, Q4_K_M), from https://github.com/XiongjieDai/GPU-Benchmarks-on-LLM-Inference.
Related: what GPU do you need for 2026 models · all builds