🔌
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 Nemotron Super v1.5?
Yes — here's how fast and up to what context, with real measured numbers.
Llama Nemotron Super v1.5 on the Apple M1 Ultra 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 48k | 5.6-6.7 t/s | ~0.1-0.1 (slow) |
| Q8 | yes | 197k | 11.1-13.4 t/s | ~0.1-0.2 (slow) |
| Q4 | yes | 263k | 19.8-23.9 t/s | ~0.2-0.3 (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 Nemotron Super v1.5?▶
Yes. At Q4 it generates ~19.8-23.9 tok/s and fits up to 263k context; beyond that it spills to SSD swap and slows to ~0.2-0.3 tok/s.
How much context fits?▶
At Q4, up to about 263k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.