Spark-X2.5-4B

Spark family · 4.0B params

Evidence: 1 sourced run · 1 independent source · first recorded Sep 2, 2026. What these labels mean.

What the Spark-X2.5-4B numbers mean

The fastest verified result on our board is 84.7 output tok/s on an RTX 3060 at Q4_K_M with a 4096-token context. That is about 11.8 ms per generated token — 500 tokens takes roughly 5.9 seconds. Prompt processing on the same record runs at 3346.7 tok/s, so a 2,000-token prompt is read in about 0.6 seconds. Peak VRAM was measured at 3.4 GB.

How much VRAM does Spark-X2.5-4B need?

Spark-X2.5-4B has 4.0B 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 Spark-X2.5-4B's parameter count. Full benchmark board.

All benchmarks Methodology