🔌
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 MI325X run OmniFusion-7B (InternViT-6B-448px V1-2)?
Yes — here's how fast and up to what context, with real measured numbers.
OmniFusion-7B (InternViT-6B-448px V1-2) on the AMD Instinct MI325X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1275k | 150.7-184.2 t/s | ~1-1.2 (slow) |
| Q8 | yes | 1352k | 301.4-368.4 t/s | ~2-2.5 (slow) |
| Q4 | yes | 1385k | 538.3-657.9 t/s | ~3.6-4.4 (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.
→ All models on the AMD Instinct MI325X
→ OmniFusion-7B (InternViT-6B-448px V1-2) specs
→ Other hardware
FAQ
Can the AMD Instinct MI325X run OmniFusion-7B (InternViT-6B-448px V1-2)?▶
Yes. At Q4 it generates ~538.3-657.9 tok/s and fits up to 1385k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.6-4.4 tok/s.
How much context fits?▶
At Q4, up to about 1385k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.