The AI Bench
12 GB · 360 GB/s

What can the NVIDIA RTX 3060 12 GB run?

The cheapest useful NVIDIA card. Fine for 8–12B models.

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 & writing13 of 25 run

  1. Gemma 4 12BRuns greatQ4_K_M · needs 8.5 GB at 8K · 30–45tok/sSmooth
  2. MiniCPM5 2BRuns greatQ8_0 · needs 4.0 GB at 8K · 65–110tok/sFast
  3. Qwen3.5 4BRuns greatQ8_0 · needs 6.4 GB at 8K · 45–70tok/sFast

Coding11 of 26 run

  1. Qwen3.5 4BRuns greatQ8_0 · needs 7.2 GB at 32K · 40–60tok/sFast
  2. Gemma 4 12BRuns wellQ4_K_M · needs 9.2 GB at 32K · 25–40tok/sSmooth
  3. Ornith 1.5 9BRuns greatQ4_K_M · needs 7.9 GB at 32K · 30–50tok/sFast

Long documents9 of 20 run

  1. Qwen3.5 4BRuns greatQ8_0 · needs 7.2 GB at 32K · 40–60tok/sFast
  2. MiniCPM5 2BRuns greatQ8_0 · needs 5.1 GB at 32K · 50–80tok/sFast
  3. Gemma 4 12BRuns wellQ4_K_M · needs 9.2 GB at 32K · 25–40tok/sSmooth

Agents & tools11 of 26 run

  1. Qwen3.5 4BRuns greatQ8_0 · needs 7.2 GB at 32K · 40–60tok/sFast
  2. MiniCPM5 2BRuns greatQ8_0 · needs 5.1 GB at 32K · 50–80tok/sFast
  3. Ornith 1.5 9BRuns greatQ4_K_M · needs 7.9 GB at 32K · 30–50tok/sFast

Images in5 of 13 run

  1. Gemma 4 12BRuns greatQ4_K_M · needs 8.5 GB at 8K · 30–45tok/sSmooth
  2. Qwen3.5 4BRuns greatQ8_0 · needs 6.4 GB at 8K · 45–70tok/sFast
  3. MiMo-V2.6 9BRuns greatQ4_K_M · needs 8.0 GB at 8K · 35–55tok/sFast

Make images4 of 6 run

  1. Stable Diffusion XL Base 1.0Runs greatFP16 · needs 7.9 GB
  2. FLUX.2 [klein] 4BRuns wellFP8 · needs 9.3 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

Gemma 4 12B (Q4_K_M, 7.1 GB file) at about 30–45tok/sSmooth.

Should you buy it?

Buy it if

You want to try local AI with 8B-class models for little money.

Skip it if

You want 20–30B models — you need 16–24 GB.

Watch out for

  • There is an 8 GB RTX 3060 too — avoid it for AI.