🔌
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 FuriosaAI RNGD run ESM3-open-small?
Yes — here's how fast and up to what context, with real measured numbers.
ESM3-open-small on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 608k | 348.2-423.2 t/s | ~9.3-11.3 (slow) |
| Q8 | yes | 630k | 696.4-846.4 t/s | ~18.6-22.6 (slow) |
| Q4 | yes | 639k | 1243.6-1511.5 t/s | ~33.2-40.3 (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 FuriosaAI RNGD run ESM3-open-small?▶
Yes. At Q4 it generates ~1243.6-1511.5 tok/s and fits up to 639k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~33.2-40.3 tok/s.
How much context fits?▶
At Q4, up to about 639k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.