🔌
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-2.8b?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-2.8b on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 5956k | 2205-2695 t/s | ~4.5-5.5 (slow) |
| Q8 | yes | 5999k | 4410-5390 t/s | ~9-11 (slow) |
| Q4 | yes | 6018k | 7875-9625 t/s | ~16.1-19.6 (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-2.8b?▶
Yes. At Q4 it generates ~7875-9625 tok/s and fits up to 6018k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~16.1-19.6 tok/s.
How much context fits?▶
At Q4, up to about 6018k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.