🔌
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 64GB run InternVL2 26B?
Yes — here's how fast and up to what context, with real measured numbers.
InternVL2 26B on the Apple M4 Max 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 19k | 7.3-8.8 t/s | ~0.1-0.2 (slow) |
| Q8 | yes | 117k | 14.6-17.6 t/s | ~0.3-0.3 (slow) |
| Q4 | yes | 160k | 26-31.4 t/s | ~0.5-0.6 (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 64GB run InternVL2 26B?▶
Yes. At Q4 it generates ~26-31.4 tok/s and fits up to 160k context; beyond that it spills to SSD swap and slows to ~0.5-0.6 tok/s.
How much context fits?▶
At Q4, up to about 160k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.