🔌
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 RWKV-6 (Finch) 3B?
Yes — here's how fast and up to what context, with real measured numbers.
RWKV-6 (Finch) 3B on the Apple M2 Ultra 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2519k | 87.7-105.8 t/s | ~1.1-1.3 (slow) |
| Q8 | yes | 2567k | 175.5-211.6 t/s | ~2.2-2.6 (slow) |
| Q4 | yes | 2587k | 313.4-377.9 t/s | ~3.9-4.7 (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 Ultra 192GB run RWKV-6 (Finch) 3B?▶
Yes. At Q4 it generates ~313.4-377.9 tok/s and fits up to 2587k context; beyond that it spills to SSD swap and slows to ~3.9-4.7 tok/s.
How much context fits?▶
At Q4, up to about 2587k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.