New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Instinct MI430X run LFM2.5-Embedding-350M?
Yes — here's how fast and up to what context, with real measured numbers.
LFM2.5-Embedding-350M on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 6031k | 20970-25630 t/s | ~36-44 (slow) |
| Q8 | yes | 6036k | 41940-51260 t/s | ~72-88 (slow) |
| Q4 | yes | 6039k | 74892.9-91535.7 t/s | ~128.6-157.1 (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 MI430X run LFM2.5-Embedding-350M?▶
Yes. At Q4 it generates ~74892.9-91535.7 tok/s and fits up to 6039k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~128.6-157.1 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.