🔌
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 Instinct MI440X run Llemma 34B?
Yes — here's how fast and up to what context, with real measured numbers.
Llemma 34B on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1251k | 181.6-221.9 t/s | ~0.4-0.5 (slow) |
| Q8 | yes | 1381k | 363.2-443.9 t/s | ~0.7-0.9 (slow) |
| Q4 | yes | 1438k | 648.5-792.6 t/s | ~1.3-1.6 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the Instinct MI440X run Llemma 34B?▶
Yes. At Q4 it generates ~648.5-792.6 tok/s and fits up to 1438k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.3-1.6 tok/s.
How much context fits?▶
At Q4, up to about 1438k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.