🔌
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 Max 96GB run Llemma 34B?
Yes — here's how fast and up to what context, with real measured numbers.
Llemma 34B on the Apple M2 Max 96GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 64k | 4-4.8 t/s | ~0.1-0.1 (slow) |
| Q8 | yes | 194k | 8-9.6 t/s | ~0.2-0.2 (slow) |
| Q4 | yes | 251k | 14.3-17.2 t/s | ~0.4-0.4 (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 M2 Max 96GB run Llemma 34B?▶
Yes. At Q4 it generates ~14.3-17.2 tok/s and fits up to 251k context; beyond that it spills to SSD swap and slows to ~0.4-0.4 tok/s.
How much context fits?▶
At Q4, up to about 251k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.