🔌
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 MI440X run XGLM-7.5B?
Yes — here's how fast and up to what context, with real measured numbers.
XGLM-7.5B on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2906k | 823.2-1006.1 t/s | ~1.7-2.1 (slow) |
| Q8 | yes | 2964k | 1646.4-2012.3 t/s | ~3.4-4.1 (slow) |
| Q4 | yes | 2989k | 2940-3593.3 t/s | ~6-7.3 (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 MI440X run XGLM-7.5B?▶
Yes. At Q4 it generates ~2940-3593.3 tok/s and fits up to 2989k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~6-7.3 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.