Ling-3.0-tiny

Ling family · 8.0B params

Evidence: 2 sourced runs · 2 awaiting review · 1 independent source · first recorded Aug 11, 2026 · last recorded Sep 1, 2026. What these labels mean.

What the Ling-3.0-tiny numbers mean

The fastest verified result on our board is 369.1 output tok/s on an RTX PRO 6000 Blackwell at Q4_K_M with a 640-token context. That is about 2.7 ms per generated token — 500 tokens takes roughly 1.4 seconds. Prompt processing on the same record runs at 20069.5 tok/s, so a 2,000-token prompt is read in about 0.1 seconds. Across the 4 records we hold for this model the range is 52.6–369.1 tok/s on 4 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Ling-3.0-tiny need?

Ling-3.0-tiny has 8.0B 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 Ling-3.0-tiny's parameter count. Full benchmark board.

All benchmarks Methodology