🔌
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 128GB run ChatGLM3-6B?
Yes — here's how fast and up to what context, with real measured numbers.
ChatGLM3-6B on the Apple M1 Ultra 128GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 776k | 45.3-54.7 t/s | ~0.6-0.7 (slow) |
| Q8 | yes | 822k | 90.7-109.3 t/s | ~1.1-1.4 (slow) |
| Q4 | yes | 842k | 161.9-195.2 t/s | ~2-2.4 (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 128GB run ChatGLM3-6B?▶
Yes. At Q4 it generates ~161.9-195.2 tok/s and fits up to 842k context; beyond that it spills to SSD swap and slows to ~2-2.4 tok/s.
How much context fits?▶
At Q4, up to about 842k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.