🔌
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 64GB run Qwen2.5-Coder (1.5B)?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen2.5-Coder (1.5B) on the Apple M2 Ultra 64GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 809k | 176.6-213 t/s | ~2.2-2.7 (slow) |
| Q8 | yes | 833k | 353.2-426 t/s | ~4.4-5.3 (slow) |
| Q4 | yes | 843k | 630.8-760.7 t/s | ~7.9-9.5 (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 64GB run Qwen2.5-Coder (1.5B)?▶
Yes. At Q4 it generates ~630.8-760.7 tok/s and fits up to 843k context; beyond that it spills to SSD swap and slows to ~7.9-9.5 tok/s.
How much context fits?▶
At Q4, up to about 843k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.