Can the NVIDIA RTX 5070 run gpt-oss 20B?
- FP16
- Q8_0
- Q6_K
- Q5_K_M
- Q4_K_M
- Q3_K_M
- Q2_K
Only just. gpt-oss 20B fits on the NVIDIA RTX 5070 at Q3_K_M, which costs noticeable quality. Expect about 229 tokens/second. A card with more memory is a better experience.
Run it with Ollama
Ollama's default gpt-oss:20b download is Q4_K_M, which needs about 13.7 GB, more than the 12 GB available. Download the Q3_K_M GGUF instead (LM Studio lists quants per model), or try a smaller context length.
New to this? Step-by-step setup for the RTX 5070
Run it in the cloud
Want full quality? Run gpt-oss 20B on a bigger rented GPU.
Rent a cloud GPU by the hour. No upfront cost, stop any time. Not sure whether to rent or buy? Compare the cost.
Memory needed by quantization
At 8,192 tokens of context. The black line marks the 12 GB the NVIDIA RTX 5070 can use.
| Quant | Quality | Memory | Fits? | Speed | |
|---|---|---|---|---|---|
| FP16 | Full quality | 42.8 GB | Too big | — | |
| Q8_0 | Near-lossless | 23.2 GB | Too big | — | |
| Q6_K | Excellent | 18.1 GB | Too big | — | |
| Q5_K_M | Very good | 15.9 GB | Too big | — | |
| Q4_K_M | Good, most popular | 13.7 GB | Too big | — | |
| Q3_K_M | Noticeably degraded | 11.2 GB | Fits | ~229 tok/s | |
| Q2_K | Heavily degraded | 8.8 GB | Fits | ~299 tok/s |
GPUs that run gpt-oss 20B comfortably
Frequently asked questions
Can NVIDIA RTX 5070 run gpt-oss 20B?
Only just. gpt-oss 20B fits on the NVIDIA RTX 5070 at Q3_K_M, which costs noticeable quality. Expect about 229 tokens/second. A card with more memory is a better experience.
How much VRAM does gpt-oss 20B need?
About 13.7 GB at Q4_K_M with 8,192 tokens of context, and about 42.8 GB at full FP16 precision.
How fast is gpt-oss 20B on the NVIDIA RTX 5070?
Roughly 229 tokens per second at Q3_K_M, estimated from the NVIDIA RTX 5070's 672 GB/s memory bandwidth.