Laguna-XS-2.1

Laguna family · 33.0B params

Evidence: 3 sourced runs · 2 awaiting review · 1 independent source · first recorded Jul 5, 2026 · last recorded Aug 17, 2026. What these labels mean.

What the Laguna-XS-2.1 numbers mean

The fastest verified result on our board is 283.1 output tok/s on an Intel Arc Pro B70 at Q5_K_M GGUF with a 131072-token context. That is about 3.5 ms per generated token — 500 tokens takes roughly 1.8 seconds. Prompt processing on the same record runs at 66.3 tok/s, so a 2,000-token prompt is read in about 30.2 seconds. Across the 5 records we hold for this model the range is 72.5–283.1 tok/s on 3 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Laguna-XS-2.1 need?

Laguna-XS-2.1 has 33.0B 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 Laguna-XS-2.1's parameter count. Full benchmark board.

All benchmarks Methodology