🔌
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 4090 run Gemma 4 31B?
Yes — here's how fast and up to what context, with real measured numbers.
Gemma 4 31B on the NVIDIA GeForce RTX 4090
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | no | — | — | — |
| Q8 | no | — | — | — |
| Q4 | yes | 12k | 42.4-50.5 t/s | ~1.7-2 (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.
Measured: Gemma 4 31B on NVIDIA GeForce RTX 4090
FAQ
Can the NVIDIA GeForce RTX 4090 run Gemma 4 31B?▶
Yes. At Q4 it generates ~42.4-50.5 tok/s and fits up to 12k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.7-2 tok/s.
How much context fits?▶
At Q4, up to about 12k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.