🔌
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 M1 Ultra 64GB run Qwen-Audio-Chat?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen-Audio-Chat on the Apple M1 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 299k | 32.2-38.8 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 363k | 64.3-77.5 t/s | ~0.8-1 (slow) |
| Q4 | yes | 392k | 114.8-138.5 t/s | ~1.4-1.7 (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 M1 Ultra 64GB run Qwen-Audio-Chat?▶
Yes. At Q4 it generates ~114.8-138.5 tok/s and fits up to 392k context; beyond that it spills to SSD swap and slows to ~1.4-1.7 tok/s.
How much context fits?▶
At Q4, up to about 392k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.