🔌
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 M1 Ultra 128GB run Llama-3.1-Minitron-4B?
Yes — here's how fast and up to what context, with real measured numbers.
Llama-3.1-Minitron-4B on the Apple M1 Ultra 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1613k | 68-82 t/s | ~0.9-1 (slow) |
| Q8 | yes | 1674k | 136-164 t/s | ~1.7-2.1 (slow) |
| Q4 | yes | 1701k | 242.9-292.9 t/s | ~3-3.7 (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 M1 Ultra 128GB run Llama-3.1-Minitron-4B?▶
Yes. At Q4 it generates ~242.9-292.9 tok/s and fits up to 1701k context; beyond that it spills to SSD swap and slows to ~3-3.7 tok/s.
How much context fits?▶
At Q4, up to about 1701k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.