🔌
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 MI455X run phi-3-small 7.4B?
Yes — here's how fast and up to what context, with real measured numbers.
phi-3-small 7.4B on the Instinct MI455X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2908k | 834.3-1019.7 t/s | ~1.7-2.1 (slow) |
| Q8 | yes | 2964k | 1668.6-2039.5 t/s | ~3.4-4.2 (slow) |
| Q4 | yes | 2989k | 2979.7-3641.9 t/s | ~6.1-7.4 (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 phi-3-small 7.4B?▶
Yes. At Q4 it generates ~2979.7-3641.9 tok/s and fits up to 2989k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.1-7.4 tok/s.
How much context fits?▶
At Q4, up to about 2989k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.