🔌
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 Typhoon 2.1 Gemma 12B?
Yes — here's how fast and up to what context, with real measured numbers.
Typhoon 2.1 Gemma 12B on the Apple M4 Max 48GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 108k | 15.5-18.7 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 181k | 30.9-37.3 t/s | ~0.6-0.7 (slow) |
| Q4 | yes | 214k | 55.3-66.6 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.
FAQ
Can the Apple M4 Max 48GB run Typhoon 2.1 Gemma 12B?▶
Yes. At Q4 it generates ~55.3-66.6 tok/s and fits up to 214k 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 214k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.