🔌
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 M2 Max 64GB run CollabLLM?
Yes — here's how fast and up to what context, with real measured numbers.
CollabLLM on the Apple M2 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 306k | 17-20.5 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 367k | 34-41 t/s | ~0.9-1 (slow) |
| Q4 | yes | 394k | 60.7-73.2 t/s | ~1.5-1.8 (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 M2 Max 64GB run CollabLLM?▶
Yes. At Q4 it generates ~60.7-73.2 tok/s and fits up to 394k context; beyond that it spills to SSD swap and slows to ~1.5-1.8 tok/s.
How much context fits?▶
At Q4, up to about 394k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.