🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Apple M4 Max 128GB run Llama 3.2 3B?
Yes — here's how fast and up to what context, with real measured numbers.
Llama 3.2 3B on the Apple M4 Max 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1637k | 57.8-69.7 t/s | ~1.1-1.3 (slow) |
| Q8 | yes | 1686k | 115.7-139.5 t/s | ~2.1-2.6 (slow) |
| Q4 | yes | 1707k | 206.5-249.1 t/s | ~3.8-4.6 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the Apple M4 Max 128GB run Llama 3.2 3B?▶
Yes. At Q4 it generates ~206.5-249.1 tok/s and fits up to 1707k context; beyond that it spills to SSD swap and slows to ~3.8-4.6 tok/s.
How much context fits?▶
At Q4, up to about 1707k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.