🔌
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 GMKtec EVO-X3 run BLOOM-560M?
Yes — here's how fast and up to what context, with real measured numbers.
BLOOM-560M on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1718k | 148.6-180.6 t/s | ~5.8-7.1 (slow) |
| Q8 | yes | 1726k | 297.1-361.1 t/s | ~11.6-14.1 (slow) |
| Q4 | yes | 1730k | 530.6-644.9 t/s | ~20.7-25.2 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to SSD swap and speed drops to the "beyond" figure.
FAQ
Can the GMKtec EVO-X3 run BLOOM-560M?▶
Yes. At Q4 it generates ~530.6-644.9 tok/s and fits up to 1730k context; beyond that it spills to SSD swap and slows to ~20.7-25.2 tok/s.
How much context fits?▶
At Q4, up to about 1730k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.