InternVL3-8B

unknown family · 8.0B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Jul 27, 2026. What these labels mean.

What the InternVL3-8B numbers mean

The fastest result on our board is 79.9 output tok/s on an RTX 3060 Ti at Q4_K_M with a 512-token context. That is about 12.5 ms per generated token — 500 tokens takes roughly 6.3 seconds. Prompt processing on the same record runs at 2963.5 tok/s, so a 2,000-token prompt is read in about 0.7 seconds. Peak VRAM was measured at 6.7 GB.

How much VRAM does InternVL3-8B need?

InternVL3-8B 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 InternVL3-8B's parameter count. Full benchmark board.

All benchmarks Methodology