Qwen3.6-27B-MTP

Qwen family · 28.0B params

Evidence: 3 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 10, 2026 · last recorded Aug 13, 2026. What these labels mean.

What the Qwen3.6-27B-MTP numbers mean

The fastest verified result on our board is 60.1 output tok/s on an RTX PRO 6000 Blackwell at Q6_K with a 131072-token context. That is about 16.6 ms per generated token — 500 tokens takes roughly 8.3 seconds. Prompt processing on the same record runs at 1856.7 tok/s, so a 2,000-token prompt is read in about 1.1 seconds. Across the 4 records we hold for this model the range is 28.3–60.1 tok/s on 4 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Qwen3.6-27B-MTP need?

Qwen3.6-27B-MTP 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 Qwen3.6-27B-MTP's parameter count. Full benchmark board.

All benchmarks Methodology