§01·compatibility · /check
gpt-oss 20B on RTX 3060
Yes — gpt-oss 20B runs on the RTX 3060 (12 GB). Fastest community-measured result: 64 tokens/s.
✓ runsllmactive30 series12GB VRAM
step-by-step recipe for this pair
gpt-oss 20B on RTX 3060: MXFP4 Chat at 64 tok/s in 12 GB via llama.cpp Expert Offload
llmintermediate12GB+
§02·benchmarks
| Task | Quant | Speed | VRAM | Works | Confidence | Source | Verified |
|---|---|---|---|---|---|---|---|
| llm | MXFP4 | 64tokens/s | ✓ | github.com· web | 2026-06-13 |
§03·how it was measured
- llmMXFP464 tokens/s
Token generation @ 16K with --n-cpu-moe 2 (official llama.cpp guide #15396, first-party RTX 3060 12GB / cc 8.6 / sm_86, QuantiusBenignus; ~600 MB VRAM spare)
recorded from github.com ↗ · verified 2026-06-13
§04·more gpt-oss 20B recipes
- 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
§05·common questions
Can you run gpt-oss 20B on RTX 3060?
Yes — gpt-oss 20B runs on the RTX 3060 (12 GB). Fastest community-measured result: 64 tokens/s.
Which quantizations have been tested for gpt-oss 20B on RTX 3060?
MXFP4 — measured in community benchmarks.
How fast is gpt-oss 20B on RTX 3060?
Up to 64 tokens/s (llm), the fastest community-measured result.
Are there step-by-step instructions for gpt-oss 20B on RTX 3060?
Yes — a step-by-step recipe documents gpt-oss 20B on the RTX 3060, linked at the top of this page.