The AI Bench
16 GB · 960 GB/s

What can the NVIDIA RTX 5080 run?

Fast, but only 16 GB. Great for models up to about 20B.

Best models for each task

Our top three for this machine. Chat and image tasks assume an 8K-token conversation; coding, documents and agents assume 32K.

Chat & writing15 of 25 run

  1. Gemma 4 12BRuns wellQ8_0 · needs 14.1 GB at 8K · 45–70tok/sFast
  2. Qwen3.8 27BRuns wellUD-IQ3_S · needs 14.5 GB at 8K · 45–70tok/sFast
  3. MiniCPM5 2BRuns greatQ8_0 · needs 4.0 GB at 8K · 160–250tok/sFast

Coding12 of 26 run

  1. Qwen3.5 4BRuns greatQ8_0 · needs 7.2 GB at 32K · 95–150tok/sFast
  2. Gemma 4 12BRuns greatQ4_K_M · needs 9.2 GB at 32K · 70–110tok/sFast
  3. Ornith 1.5 9BRuns wellQ8_0 · needs 11.9 GB at 32K · 50–80tok/sFast

Long documents9 of 20 run

  1. Qwen3.5 9BRuns wellQ8_0 · needs 12.5 GB at 32K · 50–80tok/sFast
  2. MiniCPM5 2BRuns greatQ8_0 · needs 5.1 GB at 32K · 120–200tok/sFast
  3. Gemma 4 12BRuns greatQ4_K_M · needs 9.2 GB at 32K · 70–110tok/sFast

Agents & tools12 of 26 run

  1. Qwen3.5 4BRuns greatQ8_0 · needs 7.2 GB at 32K · 95–150tok/sFast
  2. Ornith 1.5 9BRuns wellQ8_0 · needs 11.9 GB at 32K · 50–80tok/sFast
  3. MiMo-V2.6 9BRuns wellQ8_0 · needs 12.5 GB at 32K · 50–80tok/sFast

Images in6 of 13 run

  1. Qwen3.8 27BRuns wellUD-IQ3_S · needs 14.5 GB at 8K · 45–70tok/sFast
  2. Gemma 4 12BRuns wellQ8_0 · needs 14.1 GB at 8K · 45–70tok/sFast
  3. Qwen3.5 9BRuns greatQ8_0 · needs 11.7 GB at 8K · 55–90tok/sFast

Make images6 of 6 run

  1. Stable Diffusion XL Base 1.0Runs greatFP16 · needs 7.9 GB
  2. FLUX.2 [klein] 4BRuns wellBF16 · needs 14.0 GB
  3. Z-Image-TurboRuns great4-bit GGUF · needs 5.0 GB

Speak text7 of 7 run

  1. Qwen3-TTS 1.7BRuns greatBF16 · needs 5.5 GB
  2. Kokoro-82MRuns greatFP32 · needs 1.4 GB
  3. Chatterbox Multilingual V3Runs greatFull · needs 4.2 GB

Transcribe6 of 7 run

  1. Whisper large-v3-turbo (via faster-whisper)Runs greatFP16 · needs 2.6 GB
  2. Nemotron 3.5 ASR Streaming 0.6BRuns greatFP32 · needs 3.5 GB
  3. Qwen3-ASR 1.7BRuns greatBF16 · needs 5.7 GB

Biggest model it runs well

Qwen3.8 27B (UD-IQ3_S, 12.0 GB file) at about 45–70tok/sFast.

Should you buy it?

Buy it if

You also game and want the newest NVIDIA features.

Skip it if

AI is the main use: a used 24 GB card fits bigger models for less.

Watch out for

  • 16 GB is the limit; 27–32B models do not fit at Q4.