Ornith-1.0-35B

Ornith family · 35.0B params

Evidence: 2 sourced runs · 1 independent source · first recorded Jul 1, 2026 · last recorded Jul 23, 2026. What these labels mean.

What the Ornith-1.0-35B numbers mean

The fastest verified result on our board is 309.7 output tok/s on an RTX PRO 6000 Blackwell at Q4_K_M with a 524288-token context. That is about 3.2 ms per generated token — 500 tokens takes roughly 1.6 seconds. Prompt processing on the same record runs at 8996.0 tok/s, so a 2,000-token prompt is read in about 0.2 seconds. Peak VRAM was measured at 72.7 GB. Across the 2 records we hold for this model the range is 196.6–309.7 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Ornith-1.0-35B need?

Ornith-1.0-35B 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 Ornith-1.0-35B's parameter count. Full benchmark board.

All benchmarks Methodology