VibeThinker-3B

Qwen family · 3.0B params

Evidence: 1 sourced run · 1 independent source · first recorded Jun 17, 2026. What these labels mean.

What the VibeThinker-3B numbers mean

The fastest verified result on our board is 76.6 output tok/s on an RTX 5000 at Q8_0 with a 65536-token context. That is about 13.1 ms per generated token — 500 tokens takes roughly 6.5 seconds. Prompt processing on the same record runs at 1299.3 tok/s, so a 2,000-token prompt is read in about 1.5 seconds. Peak VRAM was measured at 6.1 GB.

How much VRAM does VibeThinker-3B need?

VibeThinker-3B has 3.0B parameters. These estimates use the same formula as the VRAM calculator: weights, plus about 15% for a moderate-context KV cache and runtime overhead, plus a small engine floor.

Long contexts and large batches raise the real number — read the smallest card as "possible with a reduced context". Measured throughput is on the benchmark board.

Models with a similar footprint

Ranked by distance from VibeThinker-3B's parameter count. Full benchmark board.

All benchmarks Methodology