// RUN — FITS

Can the Apple M3 Max 128GB run Code Llama-13B?

Yes — here's how fast and up to what context, with real measured numbers.

Code Llama-13B on the Apple M3 Max 128GB

QuantFits?Max contextSpeedBeyond context
FP16 yes 535k 10.5-12.6 t/s ~0.3-0.3 (slow)
Q8 yes 615k 20.9-25.2 t/s ~0.5-0.6 (slow)
Q4 yes 650k 37.4-45.1 t/s ~0.9-1.1 (slow)

Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.

→ All models on the Apple M3 Max 128GB → Code Llama-13B specs → Other hardware

FAQ

Can the Apple M3 Max 128GB run Code Llama-13B?▶

Yes. At Q4 it generates ~37.4-45.1 tok/s and fits up to 650k context; beyond that it spills to SSD swap and slows to ~0.9-1.1 tok/s.

How much context fits?▶

At Q4, up to about 650k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.