Qwen3.8-9B-Distill

Qwen family · 9.0B params

Evidence: 1 sourced run · 2 awaiting review · 1 independent source · first recorded Aug 20, 2026 · last recorded Sep 2, 2026. What these labels mean.

What the Qwen3.8-9B-Distill numbers mean

The fastest verified result on our board is 46.4 output tok/s on an RTX 2060 Super at Q6_K with a 8192-token context. That is about 21.5 ms per generated token — 500 tokens takes roughly 10.8 seconds. Prompt processing on the same record runs at 1295.0 tok/s, so a 2,000-token prompt is read in about 1.5 seconds. Peak VRAM was measured at 6.7 GB. Across the 3 records we hold for this model the range is 22.9–76.4 tok/s on 3 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Qwen3.8-9B-Distill need?

Qwen3.8-9B-Distill has 9.0B 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 Qwen3.8-9B-Distill's parameter count. Full benchmark board.

All benchmarks Methodology