🔌
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 Max 32GB run UDSMProt?
Yes — here's how fast and up to what context, with real measured numbers.
UDSMProt on the Apple M1 Max 32GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 416k | 4805-5794.3 t/s | ~120.1-144.9 (slow) |
| Q8 | yes | 416k | 9610-11588.5 t/s | ~240.3-289.7 (slow) |
| Q4 | yes | 416k | 17160.7-20693.8 t/s | ~429-517.3 (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 Max 32GB run UDSMProt?▶
Yes. At Q4 it generates ~17160.7-20693.8 tok/s and fits up to 416k context; beyond that it spills to SSD swap and slows to ~429-517.3 tok/s.
How much context fits?▶
At Q4, up to about 416k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.