Ornith-1.5-9B

Qwen family · 10.0B params

Evidence: 5 sourced runs · 3 awaiting review · 1 independent source · first recorded Aug 19, 2026 · last recorded Sep 4, 2026. What these labels mean.

What the Ornith-1.5-9B numbers mean

The fastest verified result on our board is 102.0 output tok/s on an RTX 5070 at Q4_K_M with a 2048-token context. That is about 9.8 ms per generated token — 500 tokens takes roughly 4.9 seconds. Prompt processing on the same record runs at 4046.7 tok/s, so a 2,000-token prompt is read in about 0.5 seconds. Across the 8 records we hold for this model the range is 22.9–102.0 tok/s on 8 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Ornith-1.5-9B need?

Ornith-1.5-9B has 10.0B 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-1.5-9B's parameter count. Full benchmark board.

All benchmarks Methodology