🔌
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 MI430X run TW3-JRGL-v2?
Yes — here's how fast and up to what context, with real measured numbers.
TW3-JRGL-v2 on the Instinct MI430X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 769k | 101.9-124.6 t/s | ~0.2-0.2 (slow) |
| Q8 | yes | 989k | 203.9-249.2 t/s | ~0.4-0.4 (slow) |
| Q4 | yes | 1085k | 364.1-445 t/s | ~0.6-0.8 (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 MI430X run TW3-JRGL-v2?▶
Yes. At Q4 it generates ~364.1-445 tok/s and fits up to 1085k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.6-0.8 tok/s.
How much context fits?▶
At Q4, up to about 1085k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.