New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI455X run OPT-1.3B (finetuned on PTB)?
Yes — here's how fast and up to what context, with real measured numbers.
OPT-1.3B (finetuned on PTB) on the Instinct MI455X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6002k | 4749.2-5804.6 t/s | ~9.7-11.8 (slow) |
| Q8 | yes | 6022k | 9498.5-11609.2 t/s | ~19.4-23.7 (slow) |
| Q4 | yes | 6030k | 16961.5-20730.8 t/s | ~34.6-42.3 (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 MI455X run OPT-1.3B (finetuned on PTB)?▶
Yes. At Q4 it generates ~16961.5-20730.8 tok/s and fits up to 6030k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~34.6-42.3 tok/s.
How much context fits?▶
At Q4, up to about 6030k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.