🔌
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 AMD Instinct MI300X 192GB run InternVL2 26B?
Yes — here's how fast and up to what context, with real measured numbers.
InternVL2 26B on the AMD Instinct MI300X 192GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 474k | 65.5-80 t/s | ~0.5-0.6 (slow) |
| Q8 | yes | 571k | 130.9-160 t/s | ~1-1.2 (slow) |
| Q4 | yes | 614k | 233.8-285.8 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 AMD Instinct MI300X 192GB run InternVL2 26B?▶
Yes. At Q4 it generates ~233.8-285.8 tok/s and fits up to 614k 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 614k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.