🔌
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 LFM2.5-ColBERT-350M?
Yes — here's how fast and up to what context, with real measured numbers.
LFM2.5-ColBERT-350M on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 640k | 1392.9-1692.9 t/s | ~37.1-45.1 (slow) |
| Q8 | yes | 646k | 2785.7-3385.7 t/s | ~74.3-90.3 (slow) |
| Q4 | yes | 648k | 4974.5-6045.9 t/s | ~132.7-161.2 (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 LFM2.5-ColBERT-350M?▶
Yes. At Q4 it generates ~4974.5-6045.9 tok/s and fits up to 648k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~132.7-161.2 tok/s.
How much context fits?▶
At Q4, up to about 648k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.