Can the RTX 5090 run gpt-oss-120b?
Not fully, but it's usable. gpt-oss-120b needs about 71.8 GB at Q4_K_M and the RTX 5090 has 32 GB - yet as a mixture-of-experts model it reads only ~5.1B parameters per token, so you can keep attention on the GPU and the experts in system RAM (llama.cpp --n-cpu-moe) and still get interactive speeds with 32 GB+ of RAM.
Every quantization
gpt-oss-120b (120.4B, 5.1B active) on 32 GB
| Quant | Weights | Needs | Fit | Est. speed |
|---|---|---|---|---|
| Q4_K_M | 70 GB | 71.8 GB | Too big | - |
| Q5_K_M | 85 GB | 86.8 GB | Too big | - |
| Q8_0 | 129 GB | 130.8 GB | Too big | - |
| FP16 | 241 GB | 242.8 GB | Too big | - |
Estimates. Needs = weights + 1.8 GB for KV cache and runtime at modest context. Speed is single-stream decode scaled from the RTX 5090's 1792 GB/s bandwidth (Estimated from memory bandwidth (llama.cpp decode)). Long contexts need more memory and run slower.
What to do instead
Two ways forward
Cheapest cards that run it
- Mac Studio M4 Ultra - 192 GB, ~$4,699
Models that fit the RTX 5090
- Qwen3.6 35B A3B - 36B, 21 GB at Q4
- Qwen3.5 35B A3B - 36B, 21 GB at Q4
- dolphin-2.9.1-yi-1.5-34b - 34.4B, 20 GB at Q4
- Gemma 4 31B - 32.7B, 19 GB at Q4
Compare
Same model, other hardware - and other models on this card
gpt-oss-120b on other hardware
- RTX 6000D~202 tok/s
- DGX Spark (GB10)~35 tok/s
- RTX Spark N1X (128 GB)~35 tok/s
Also runs on the RTX 5090
- Qwen3.6 35B A3B~391 tok/s
- Qwen3.5 35B A3B~391 tok/s
- dolphin-2.9.1-yi-1.5-34b~51 tok/s
- Gemma 4 31B~54 tok/s
- Qwen3 32B~54 tok/s
- GLM-4.7-Flash~396 tok/s
- Qwen3-30B-A3B-Instruct-2507~387 tok/s
- Qwen3.6 27B~64 tok/s
Frequently asked
Quick answers
Can the NVIDIA RTX 5090 run gpt-oss-120b?
Not fully, but it's usable. gpt-oss-120b needs about 71.8 GB at Q4_K_M and the RTX 5090 has 32 GB - yet as a mixture-of-experts model it reads only ~5.1B parameters per token, so you can keep attention on the GPU and the experts in system RAM (llama.cpp --n-cpu-moe) and still get interactive speeds with 32 GB+ of RAM.
How much VRAM does gpt-oss-120b need?
About 70 GB of weights at Q4_K_M, 129 GB at Q8_0 and 241 GB at FP16. Add roughly 1.8 GB for the KV cache and runtime at modest context lengths.
How fast is gpt-oss-120b on the RTX 5090?
It doesn't fit in the RTX 5090's memory, so speed depends on how many layers you offload to system RAM - typically single-digit tokens per second or lower.