KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM

Qwen family · 35.0B params

Evidence: 1 sourced run · 1 independent source · first recorded Aug 17, 2026. What these labels mean.

What the KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM numbers mean

The fastest verified result on our board is 201.2 output tok/s on an RTX 5090 at W4A16 with a 2048-token context. That is about 5.0 ms per generated token — 500 tokens takes roughly 2.5 seconds. Prompt processing on the same record runs at 26.9 tok/s, so a 2,000-token prompt is read in about 74.3 seconds.

How much VRAM does KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM need?

KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM has 35.0B 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 KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM's parameter count. Full benchmark board.

All benchmarks Methodology