Ornith-1.5-35B-A3B-MTP

Qwen family · 36.0B params

Evidence: 0 sourced runs · 2 awaiting review · 1 independent source · first recorded Aug 28, 2026 · last recorded Sep 4, 2026. What these labels mean.

What the Ornith-1.5-35B-A3B-MTP numbers mean

The fastest result on our board is 55.3 output tok/s on an RTX 4070 at Q4_K_M with a 102400-token context. That is about 18.1 ms per generated token — 500 tokens takes roughly 9.0 seconds. Prompt processing on the same record runs at 585.6 tok/s, so a 2,000-token prompt is read in about 3.4 seconds. Peak VRAM was measured at 11.8 GB. Across the 2 records we hold for this model the range is 33.2–55.3 tok/s on 2 GPUs, because quantisation, context length and the engine build all move the number.

How much VRAM does Ornith-1.5-35B-A3B-MTP need?

Ornith-1.5-35B-A3B-MTP has 36.0B 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-1.5-35B-A3B-MTP's parameter count. Full benchmark board.

All benchmarks Methodology