🔌
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 Ultra 192GB run OmniFusion-7B (InternViT-6B-448px V1-2)?
Yes — here's how fast and up to what context, with real measured numbers.
OmniFusion-7B (InternViT-6B-448px V1-2) on the Apple M2 Ultra 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 892k | 21.7-26.2 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 969k | 43.4-52.3 t/s | ~0.5-0.7 (slow) |
| Q4 | yes | 1003k | 77.5-93.4 t/s | ~1-1.2 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
→ All models on the Apple M2 Ultra 192GB
→ OmniFusion-7B (InternViT-6B-448px V1-2) specs
→ Other hardware
FAQ
Can the Apple M2 Ultra 192GB run OmniFusion-7B (InternViT-6B-448px V1-2)?▶
Yes. At Q4 it generates ~77.5-93.4 tok/s and fits up to 1003k context; beyond that it spills to SSD swap and slows to ~1-1.2 tok/s.
How much context fits?▶
At Q4, up to about 1003k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.