Qwen3.6-27B-i1

Qwen family · 28.0B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 14, 2026. What these labels mean.

What the Qwen3.6-27B-i1 numbers mean

The fastest result on our board is 15.5 output tok/s on an RTX 4070 at IQ1_S with a 196608-token context. That is about 64.7 ms per generated token — 500 tokens takes roughly 32.4 seconds. Prompt processing on the same record runs at 220.1 tok/s, so a 2,000-token prompt is read in about 9.1 seconds. Peak VRAM was measured at 11.4 GB.

How much VRAM does Qwen3.6-27B-i1 need?

Qwen3.6-27B-i1 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-i1's parameter count. Full benchmark board.

All benchmarks Methodology