§01·compatibility · /check
gpt-oss 20B on RTX 5070 Ti
Yes — gpt-oss 20B runs on the RTX 5070 Ti (16 GB). Fastest community-measured result: 6178.3 prefill tokens/s, with 16 GB peak VRAM.
✓ runsllmactive50 series16GB VRAM
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| llm | MXFP4 | 6178.3prefill tokens/s | 16GB | ✓ | hardware-corner.net· web | 2026-05-15 | |
| llm | MXFP4 | 156tokens/s | 16GB | ✓ | hardware-corner.net· web | 2026-05-15 |
§03·common questions
Can you run gpt-oss 20B on RTX 5070 Ti?
Yes — gpt-oss 20B runs on the RTX 5070 Ti (16 GB). Fastest community-measured result: 6178.3 prefill tokens/s, with 16 GB peak VRAM.
How much VRAM does gpt-oss 20B need on RTX 5070 Ti?
Measured peak VRAM is 16 GB.
Which quantizations have been tested for gpt-oss 20B on RTX 5070 Ti?
MXFP4 — measured in community benchmarks.
How fast is gpt-oss 20B on RTX 5070 Ti?
Up to 6178.3 prefill tokens/s (llm), the fastest community-measured result.
Are there step-by-step instructions for gpt-oss 20B on RTX 5070 Ti?
Yes — a step-by-step recipe documents gpt-oss 20B on the RTX 5070 Ti; see the recipes listed below.
§04·related recipes
- llmbeginner16GB+
gpt-oss 20B on RTX 5070 Ti: MXFP4 Chat at 156 tok/s via Ollama or vLLM
- llmbeginner16GB+
gpt-oss 20B on RTX 5060 Ti: MXFP4 Chat at 92 tok/s via Ollama or vLLM
- llmbeginner16GB+
gpt-oss 20B on RTX 4060 Ti 16GB: MXFP4 chat at 63 tok/s via Ollama or vLLM
- llmintermediate13GB+
gpt-oss 20B on Apple M2 Pro: running 20B in 16 GB unified memory with the wired-limit raise
- llmbeginner13GB+
gpt-oss 20B on Apple M3 Max: native-MXFP4 chat in 48 GB unified memory with MLX