Written by Jakub Rusinowski · Last updated August 15, 2026
Yes, but it is tight
Yes, but it is tight — GPT-OSS 20B at Q5_K_M needs about 15.4 GB of the 16 GB usable on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM), leaving only ~0.6 GB before the runtime starts swapping. Expect ~45 tok/s (estimated), with room for about 16,384 tokens of context.
Confidence: medium · Recommended quantization: Q5_K_M · Estimated speed: ~45 tok/s
| Usable memory for models | 16 GB |
| Memory bandwidth | 960 GB/s |
| Form factor | Desktop |
| Operating system | Windows or Linux |
| Memory upgradeable | Yes |
| Quant | Memory needed | Fits 16 GB? | Max context | Est. speed | Download |
|---|---|---|---|---|---|
| F16 | 41.2 GB | ✗ No | — | — | 40 GB |
| Q8_0 | 22.5 GB | ✗ No | — | — | 21.3 GB |
| Q6_K | 17.6 GB | ✗ No | — | — | 16.4 GB |
| Q5_K_M | 15.4 GB | ✓ Yes | 16K | ~45 tok/s | 14.2 GB |
| Q4_K_M | 13.3 GB | ✓ Yes | 32K | ~51.8 tok/s | 12.1 GB |
| Q3_K_M | 9.7 GB | ✓ Yes | 128K | ~69.6 tok/s | 8.5 GB |
| Q2_K | 7.8 GB | ✓ Yes | 128K | ~85.8 tok/s | 6.6 GB |
| Variant | Needs at Q4_K_M | Fits? | Est. speed |
|---|---|---|---|
| GPT-oss 120B | 73.9 GB | ✗ Too large | — |
| GPT-OSS 20B | 13.3 GB | ✓ Fits | ~51.8 tok/s |
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving
Yes, but it is tight — GPT-OSS 20B at Q5_K_M needs about 15.4 GB of the 16 GB usable on RTX 5080 Desktop (16 GB VRAM, 32 GB RAM), leaving only ~0.6 GB before the runtime starts swapping. Expect ~45 tok/s (estimated), with room for about 16,384 tokens of context.
Q5_K_M — it needs about 15.4 GB of the 16 GB available, downloads as roughly 14.2 GB, and runs at an estimated 45 tokens/sec with up to 16K of context.
Nothing binding — the model fits with headroom and generates at a usable speed on this hardware.
Ollama or llama.cpp (CUDA/ROCm) — vLLM if you need concurrent serving