🔌
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 96GB run GTE-ModernColBERT-v1?
Yes — here's how fast and up to what context, with real measured numbers.
GTE-ModernColBERT-v1 on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1291k | 912.8-1100.7 t/s | ~22.8-27.5 (slow) |
| Q8 | yes | 1293k | 1825.5-2201.3 t/s | ~45.6-55 (slow) |
| Q4 | yes | 1294k | 3259.8-3931 t/s | ~81.5-98.3 (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 M2 Max 96GB run GTE-ModernColBERT-v1?▶
Yes. At Q4 it generates ~3259.8-3931 tok/s and fits up to 1294k context; beyond that it spills to SSD swap and slows to ~81.5-98.3 tok/s.
How much context fits?▶
At Q4, up to about 1294k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.