🔌
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 M3 Max 36GB 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 M3 Max 36GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 36k | 8.1-9.8 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 112k | 16.3-19.6 t/s | ~0.5-0.7 (slow) |
| Q4 | yes | 146k | 29-35 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 M3 Max 36GB
→ OmniFusion-7B (InternViT-6B-448px V1-2) specs
→ Other hardware
FAQ
Can the Apple M3 Max 36GB run OmniFusion-7B (InternViT-6B-448px V1-2)?▶
Yes. At Q4 it generates ~29-35 tok/s and fits up to 146k 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 146k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.