🔌
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 ChatGLM3-6B?
Yes — here's how fast and up to what context, with real measured numbers.
ChatGLM3-6B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 234k | 81.3-98.8 t/s | ~2.2-2.6 (slow) |
| Q8 | yes | 280k | 162.5-197.5 t/s | ~4.3-5.3 (slow) |
| Q4 | yes | 300k | 290.2-352.7 t/s | ~7.7-9.4 (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 ChatGLM3-6B?▶
Yes. At Q4 it generates ~290.2-352.7 tok/s and fits up to 300k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.7-9.4 tok/s.
How much context fits?▶
At Q4, up to about 300k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.