Qwen Image 2.1 benchmarks

Test hardware and platform limits.

Leaf control: Windows and native Linux use Diffusers leaf offloading with use_stream=True. WSL uses use_stream=False because streamed leaf offloading was incompatible with the tested WSL environment; this is not a limitation established for every WSL setup. This setting concerns weight offloading, not video VAE decode streaming.

Base BF16, 512×512, 20 steps, seed 42, capybara prompt, CFG 1 and KV cache. Shared official leaf text encoder; resident untiled VAE on Windows/Linux, untiled non-streamed leaf VAE on WSL.

Presets resolve to the executed transformer runtimes; the VAE route is independent. Scenario names link directly to measurement details. Times are seconds; GPU is sampled absolute driver usage, RAM is process RSS, and memory units are GiB. Average is denoise wall divided by steps, including warmup, not completed warm GPU timing. Tracked total excludes command startup and downloads. Before reading the tables, see the labels and memory glossary.

In comparable overview tables, official Diffusers leaf is the first row and the reference for that table: 🟢 ↓ is lower, 🔴 ↑ is higher. Equal displayed values have no arrow. Arrows describe measurements, not an overall preset ranking; higher memory can accompany faster execution. Phase tables and separate workloads without a leaf control have no arrows. Rows with different driver/cache sessions or a reused non-side-by-side observation also have no arrows.

Windows — BF16

Phase-table rows identify the complete pipeline by its transformer route. Encoder and VAE strategies remain those stated for each platform; a row labeled vmm_fast does not imply native VMM execution in every phase.

The native row is a reused official-package observation, not a repeat alongside the other routes.

Phase measurements

These are selected separately monitored phases, not an additive decomposition of the tracked total. Cleanup, saving and other unlisted setup remain in the total.

Text encoder load

Text encoder attachment

Text encode

Text encoder cleanup

Transformer load

Transformer attachment

Denoise/readback

VAE load

VAE decode

Pipeline total

Measured tracked totals and global peaks for the same complete runs above. These are not sums of the phase tables. The encoder and VAE routes remain as stated for this workload; the runtime column identifies the transformer.

Linux — BF16

The NVMe observation uses a different driver/cache session from the route trio; it is not a controlled allocator-only A/B.

Phase measurements

These are selected separately monitored phases, not an additive decomposition of the tracked total. Cleanup, saving and other unlisted setup remain in the total.

Text encoder load

Text encoder attachment

Text encode

Text encoder cleanup

Transformer load

Transformer attachment

Denoise/readback

VAE load

VAE decode

Pipeline total

Measured tracked totals and global peaks for the same complete runs above. These are not sums of the phase tables. The encoder and VAE routes remain as stated for this workload; the runtime column identifies the transformer.

WSL — BF16

Leaf controls are non-streamed; linear uses an explicit 3 GiB override and native uses bounded registration. These are not Windows/Linux parity claims.

Phase measurements

These are selected separately monitored phases, not an additive decomposition of the tracked total. Cleanup, saving and other unlisted setup remain in the total.

Text encoder load

Text encoder attachment

Text encode

Text encoder cleanup

Transformer load

Transformer attachment

Denoise/readback

VAE load

VAE decode

Pipeline total

Measured tracked totals and global peaks for the same complete runs above. These are not sums of the phase tables. The encoder and VAE routes remain as stated for this workload; the runtime column identifies the transformer.

Windows 1024×1024 — separate VAE settings

Base BF16, 20 steps, seed 42; untiled leaf VAE. Native uses explicit cache trimming; this is not an allocator-only A/B.

Phase measurements

Windows SDNQ INT4

Base 512×512, 20 steps, seed 42; BF16 auxiliaries, resident stock VAE. Output parity is within the INT4 pair, not a BF16 quality-equivalence claim.

Phase measurements

Recommendations

The common text encoder dominates global RSS in several cases. Around 19–22 GiB process RSS does not establish fit on a 16 GiB RAM computer.

Single observations, not statistical or arbitrary-model guarantees. Missing measurements are unavailable, not zero; phase peaks must not be summed. See presets, reproduction and measurement details before comparing different recipes.