Can I run it?
Can I run gpt oss 20b on GeForce RTX 5080?
Runs
Runs fully on your GeForce RTX 5080 at Q5_K_M, 8K context, about 83–113 tok/s. Weights 10.9 GB plus 0.19 GB of KV cache — 11.5 GB of 14.7 GB usable. Up to 128K context still fits.
Best quantQ5_K_M
Working context8K
Max that fits128K
Speed83–113 tok/sEstimate from memory bandwidth, not a benchmark. Method.
Weights10.9 GB
KV cache0.19 GB
Total11.5 GB
Usable14.7 GB
gpt oss 20b details · GeForce RTX 5080 page · How this estimate is made
Run commands
llama.cpp
llama-server -hf unsloth/gpt-oss-20b-GGUF:Q5_K_M -c 8192 -ngl 24
No matching name in the Ollama library snapshot.
LM Studio
lms get unsloth/gpt-oss-20b-GGUF # Then load quant Q5_K_M
Assumptions
- Estimate from memory bandwidth, not a benchmark. Decode speed uses 55–75% of peak bandwidth.
- KV cache is FP16. Engine overhead assumes llama.cpp (0.3 GB + 1% of the weights). Ollama is closer to 0.9 GB + 3%, LM Studio closer to 1 GB + 3%.
- Q5_K_M size is the real GGUF file size from Hugging Face.
- 0.5 GB is reserved because this GPU also drives a display, then 5% of the rest is left free.
- Speed is quoted at 8K context, not at the maximum context that still fits.
Larger models that also fit
- Can I run Qwen3.8 27B on GeForce RTX 5080? — Tight fit, UD-IQ4_XS, 36–49 tok/s (estimate)
- Can I run Qwen3.6 35B A3B on GeForce RTX 5080? — Tight fit, UD-IQ3_S, 92–126 tok/s (estimate)
- Can I run Qwen3.8 35B A3B Distill on GeForce RTX 5080? — Tight fit, Q2_K, 91–124 tok/s (estimate)
Updated 2026-10-24. Profile on this page is the device default plus 32 GB of DDR5-5600 system RAM.