🔌
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 ESM1b?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1b on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 631k | 747.2-908.2 t/s | ~19.9-24.2 (slow) |
| Q8 | yes | 641k | 1494.5-1816.4 t/s | ~39.9-48.4 (slow) |
| Q4 | yes | 645k | 2668.7-3243.5 t/s | ~71.2-86.5 (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 ESM1b?▶
Yes. At Q4 it generates ~2668.7-3243.5 tok/s and fits up to 645k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~71.2-86.5 tok/s.
How much context fits?▶
At Q4, up to about 645k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.