New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI440X run TiTok-L?
Yes — here's how fast and up to what context, with real measured numbers.
TiTok-L on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6032k | 20110.7-24579.8 t/s | ~41-50.2 (slow) |
| Q8 | yes | 6037k | 40221.5-49159.6 t/s | ~82.1-100.3 (slow) |
| Q4 | yes | 6039k | 71824.1-87785 t/s | ~146.6-179.2 (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 MI440X run TiTok-L?▶
Yes. At Q4 it generates ~71824.1-87785 tok/s and fits up to 6039k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~146.6-179.2 tok/s.
How much context fits?▶
At Q4, up to about 6039k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.