🔌
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 MI430X run XGen-7B?
Yes — here's how fast and up to what context, with real measured numbers.
XGen-7B on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2919k | 1095.4-1338.9 t/s | ~1.9-2.3 (slow) |
| Q8 | yes | 2970k | 2190.9-2677.8 t/s | ~3.8-4.6 (slow) |
| Q4 | yes | 2992k | 3912.3-4781.7 t/s | ~6.7-8.2 (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 MI430X run XGen-7B?▶
Yes. At Q4 it generates ~3912.3-4781.7 tok/s and fits up to 2992k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6.7-8.2 tok/s.
How much context fits?▶
At Q4, up to about 2992k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.