Qwen3-4B-Thinking-2507

Qwen family · 4.0B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 17, 2026. What these labels mean.

What the Qwen3-4B-Thinking-2507 numbers mean

The fastest result on our board is 219.7 output tok/s on an RTX 5090 at Q8_0 with a 2048-token context. That is about 4.6 ms per generated token — 500 tokens takes roughly 2.3 seconds. Prompt processing on the same record runs at 1053.7 tok/s, so a 2,000-token prompt is read in about 1.9 seconds.

How much VRAM does Qwen3-4B-Thinking-2507 need?

Qwen3-4B-Thinking-2507 has 4.0B 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 Qwen3-4B-Thinking-2507's parameter count. Full benchmark board.

All benchmarks Methodology