🔌
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 Instinct MI440X run InternVL2_5-26B?
Yes — here's how fast and up to what context, with real measured numbers.
InternVL2_5-26B on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1316k | 242.1-295.9 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 1413k | 484.2-591.8 t/s | ~1-1.2 (slow) |
| Q4 | yes | 1456k | 864.7-1056.9 t/s | ~1.8-2.2 (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 Instinct MI440X run InternVL2_5-26B?▶
Yes. At Q4 it generates ~864.7-1056.9 tok/s and fits up to 1456k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.8-2.2 tok/s.
How much context fits?▶
At Q4, up to about 1456k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.