🔌
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 Radeon RX 9070 XT run Transformer (Adaptive Input Embeddings) WT103?
Yes — here's how fast and up to what context, with real measured numbers.
Transformer (Adaptive Input Embeddings) WT103 on the AMD Radeon RX 9070 XT
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 194k | 821.3-1003.8 t/s | ~51-62.3 (slow) |
| Q8 | yes | 198k | 1642.6-2007.6 t/s | ~102-124.7 (slow) |
| Q4 | yes | 200k | 2933.2-3585 t/s | ~182.2-222.7 (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 Radeon RX 9070 XT
→ Transformer (Adaptive Input Embeddings) WT103 specs
→ Other hardware
FAQ
Can the AMD Radeon RX 9070 XT run Transformer (Adaptive Input Embeddings) WT103?▶
Yes. At Q4 it generates ~2933.2-3585 tok/s and fits up to 200k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~182.2-222.7 tok/s.
How much context fits?▶
At Q4, up to about 200k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.