Bonsai-27B

Qwen family · 28.0B params

Evidence: 1 sourced run · 1 awaiting review · 1 independent source · first recorded Aug 17, 2026 · last recorded Aug 18, 2026. What these labels mean.

What the Bonsai-27B numbers mean

The fastest verified result on our board is 72.9 output tok/s on an RTX 3080 at Q1_0 with a 32768-token context. That is about 13.7 ms per generated token — 500 tokens takes roughly 6.9 seconds. Prompt processing on the same record runs at 1319.8 tok/s, so a 2,000-token prompt is read in about 1.5 seconds. Peak VRAM was measured at 5.1 GB. Across the 2 records we hold for this model the range is 72.9–136.7 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Bonsai-27B need?

Bonsai-27B has 28.0B 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 Bonsai-27B's parameter count. Full benchmark board.

All benchmarks Methodology