Hy3

Hunyuan family · 299.0B params

Evidence: 1 sourced run · 1 independent source · first recorded Sep 4, 2026. What these labels mean.

What the Hy3 numbers mean

The fastest verified result on our board is 27.6 output tok/s on an CMP 170HX x2 at Q2_K_XL with a 32768-token context. That is about 36.2 ms per generated token — 500 tokens takes roughly 18.1 seconds. Prompt processing on the same record runs at 250.7 tok/s, so a 2,000-token prompt is read in about 8.0 seconds. Peak VRAM was measured at 115.9 GB.

How much VRAM does Hy3 need?

Hy3 has 299.0B 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 Hy3's parameter count. Full benchmark board.

All benchmarks Methodology