🔌
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 Pythia-1.4b?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-1.4b on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 5999k | 4410-5390 t/s | ~9-11 (slow) |
| Q8 | yes | 6020k | 8820-10780 t/s | ~18-22 (slow) |
| Q4 | yes | 6030k | 15750-19250 t/s | ~32.1-39.3 (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 Pythia-1.4b?▶
Yes. At Q4 it generates ~15750-19250 tok/s and fits up to 6030k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~32.1-39.3 tok/s.
How much context fits?▶
At Q4, up to about 6030k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.