🔌
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 NVIDIA GeForce RTX 3070 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 NVIDIA GeForce RTX 3070
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 82k | 662-789 t/s | ~59.1-70.4 (slow) |
| Q8 | yes | 86k | 1324-1578 t/s | ~118.2-140.9 (slow) |
| Q4 | yes | 87k | 2364.4-2817.8 t/s | ~211.1-251.6 (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 NVIDIA GeForce RTX 3070
→ Transformer (Adaptive Input Embeddings) WT103 specs
→ Other hardware
FAQ
Can the NVIDIA GeForce RTX 3070 run Transformer (Adaptive Input Embeddings) WT103?▶
Yes. At Q4 it generates ~2364.4-2817.8 tok/s and fits up to 87k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~211.1-251.6 tok/s.
How much context fits?▶
At Q4, up to about 87k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.