🔌
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 M4 Max 48GB run GTE-ModernColBERT-v1?
Yes — here's how fast and up to what context, with real measured numbers.
GTE-ModernColBERT-v1 on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 632k | 1245.9-1502.4 t/s | ~22.8-27.5 (slow) |
| Q8 | yes | 634k | 2491.8-3004.8 t/s | ~45.6-55 (slow) |
| Q4 | yes | 635k | 4449.7-5365.8 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 M4 Max 48GB run GTE-ModernColBERT-v1?▶
Yes. At Q4 it generates ~4449.7-5365.8 tok/s and fits up to 635k 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 635k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.