🔌
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 AMD Instinct MI455X run SGPT BE 5.8B?
Yes — here's how fast and up to what context, with real measured numbers.
SGPT BE 5.8B on the AMD Instinct MI455X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2932k | 1064.5-1301 t/s | ~2.2-2.7 (slow) |
| Q8 | yes | 2977k | 2129-2602.1 t/s | ~4.3-5.3 (slow) |
| Q4 | yes | 2996k | 3801.7-4646.6 t/s | ~7.8-9.5 (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 MI455X run SGPT BE 5.8B?▶
Yes. At Q4 it generates ~3801.7-4646.6 tok/s and fits up to 2996k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.8-9.5 tok/s.
How much context fits?▶
At Q4, up to about 2996k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.