BTL-4-Compact

Llama family · 35.0B params

Evidence: 0 sourced runs · 1 awaiting review · 1 independent source · first recorded Aug 9, 2026. What these labels mean.

What the BTL-4-Compact numbers mean

The fastest result on our board is 58.5 output tok/s on an RTX 4070 at IQ2_XXS with a 131072-token context. That is about 17.1 ms per generated token — 500 tokens takes roughly 8.5 seconds. Prompt processing on the same record runs at 1336.6 tok/s, so a 2,000-token prompt is read in about 1.5 seconds. Peak VRAM was measured at 11.9 GB.

How much VRAM does BTL-4-Compact need?

BTL-4-Compact 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 BTL-4-Compact's parameter count. Full benchmark board.

All benchmarks Methodology