Qwen3-30B-A3B-Thinking-2507

Qwen family · 31.0B params

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

What the Qwen3-30B-A3B-Thinking-2507 numbers mean

The fastest verified result on our board is 94.3 output tok/s on an RTX 3060 x2 at Q4_K_M with a 65536-token context. That is about 10.6 ms per generated token — 500 tokens takes roughly 5.3 seconds. Prompt processing on the same record runs at 1073.4 tok/s, so a 2,000-token prompt is read in about 1.9 seconds. Peak VRAM was measured at 20.1 GB.

How much VRAM does Qwen3-30B-A3B-Thinking-2507 need?

Qwen3-30B-A3B-Thinking-2507 has 31.0B 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 Qwen3-30B-A3B-Thinking-2507's parameter count. Full benchmark board.

All benchmarks Methodology