AMD Radeon RX 7900 XTX × gpt-oss-20b (MoE)
Can the RX 7900 XTX run gpt-oss-20b (MoE)?
Yes
Yes. The RX 7900 XTX can run gpt-oss-20b (MoE) at up to MXFP4 (native) (needs ~14.6 GB of 22.8 GB usable), at an estimated ~169 tokens/sec at MXFP4 (native).
Speed is estimated from memory bandwidth (no measured benchmark for this device). No direct public benchmark of this exact pair is recorded yet.
By quantization (8K context)
| Quant | Memory needed | Fits? | Est. tok/s |
|---|---|---|---|
| MXFP4 (native) | 14.6 GB | ✅ | ~169 |
Fastest hardware for gpt-oss-20b (MoE)
- NVIDIA GeForce RTX 5090 — ~267 tok/s at MXFP4 (native)
- NVIDIA GeForce RTX 4090 — ~171 tok/s at MXFP4 (native)
- NVIDIA GeForce RTX 5080 — ~167 tok/s at MXFP4 (native)
- NVIDIA GeForce RTX 5070 Ti — ~163 tok/s at MXFP4 (native)
- NVIDIA GeForce RTX 3090 Ti — ~157 tok/s at MXFP4 (native)
No suitable GPU? Rent one by the hour on Vast.ai or RunPod (affiliate links).
Get new models & benchmarks in your inbox
No spam. Unsubscribe anytime by replying to any email.