🔌
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 Max 64GB run Llemma 7B?
Yes — here's how fast and up to what context, with real measured numbers.
Llemma 7B on the Apple M1 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 321k | 19.4-23.4 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 375k | 38.9-46.9 t/s | ~1-1.2 (slow) |
| Q4 | yes | 398k | 69.4-83.7 t/s | ~1.7-2.1 (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 Max 64GB run Llemma 7B?▶
Yes. At Q4 it generates ~69.4-83.7 tok/s and fits up to 398k context; beyond that it spills to SSD swap and slows to ~1.7-2.1 tok/s.
How much context fits?▶
At Q4, up to about 398k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.