🔌
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 TiTok-L?
Yes — here's how fast and up to what context, with real measured numbers.
TiTok-L on the GMKtec EVO-X3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1726k | 271-329.4 t/s | ~10.6-12.9 (slow) |
| Q8 | yes | 1730k | 542-658.8 t/s | ~21.2-25.7 (slow) |
| Q4 | yes | 1732k | 967.9-1176.4 t/s | ~37.8-46 (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 TiTok-L?▶
Yes. At Q4 it generates ~967.9-1176.4 tok/s and fits up to 1732k context; beyond that it spills to SSD swap and slows to ~37.8-46 tok/s.
How much context fits?▶
At Q4, up to about 1732k tokens stay in fast memory; longer context spills to SSD swap and throughput collapses.