Qwen3.8-Flash-Next-hibrid48

Qwen family · 180.0B params

Evidence: 5 sourced runs · 1 independent source · first recorded Sep 14, 2026 · last recorded Sep 28, 2026. What these labels mean.

What the Qwen3.8-Flash-Next-hibrid48 numbers mean

The fastest verified result on our board is 474.0 output tok/s on an DGX Spark x2 at NVFP4 (output head) with a 262144-token context. That is about 2.1 ms per generated token — 500 tokens takes roughly 1.1 seconds. Across the 5 records we hold for this model the range is 60.0–474.0 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Qwen3.8-Flash-Next-hibrid48 need?

Qwen3.8-Flash-Next-hibrid48 has 180.0B 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-Flash-Next-hibrid48's parameter count. Full benchmark board.

All benchmarks Methodology