New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the AMD Instinct MI300X 192GB run ALBERT-xxlarge?
Yes — here's how fast and up to what context, with real measured numbers.
ALBERT-xxlarge on the AMD Instinct MI300X 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2665k | 7104.3-8683 t/s | ~53.6-65.5 (slow) |
| Q8 | yes | 2669k | 14208.5-17366 t/s | ~107.2-131.1 (slow) |
| Q4 | yes | 2670k | 25372.3-31010.6 t/s | ~191.5-234 (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 AMD Instinct MI300X 192GB run ALBERT-xxlarge?▶
Yes. At Q4 it generates ~25372.3-31010.6 tok/s and fits up to 2670k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~191.5-234 tok/s.
How much context fits?▶
At Q4, up to about 2670k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.