RTX 5080 for local LLMs

3 measured results from 2 builds, each linked to its source.

Can it run? Qwen3.8 Flash-Next on 2x RTX 5080 gpt-oss 20B on RTX 5080

All builds with the RTX 5080

All measured results

Hide speculative-decoding results ⚡ (MTP, DFlash, DSpark and similar draft-and-verify methods give much higher tok/s on predictable text and are not comparable 1:1 with plain decode)

All RTX 5080 builds: see also all GPUs · best LLMs by memory size · download the dataset.

FAQ

How fast is the RTX 5080 for local LLMs?

The fastest plain-decode result we have is 204.85 tok/s on gpt-oss 20B (MXFP4, llama.cpp) in Single RTX 5080 16GB. Speed depends heavily on the model, quant and engine, so compare like with like in the table. RigBase lists 3 measured results from 2 builds.

How much memory does the RTX 5080 have?

16 GB per card. Memory bandwidth: 960 GB/s (memory bandwidth as listed on llamabench).

Which models have been measured on the RTX 5080?

Qwen3.8 Flash-Next, gpt-oss 20B.

Where do these numbers come from?

Every row links to a build page with its original public source (benchmark logs, READMEs, forum posts). RigBase does not re-run the benchmarks. Results marked ⚡ use speculative decoding and are not comparable 1:1 with plain decode.