Pair

Qwen3.6-35B-A3B

Name: OpenWeights Terminal measured pairs
Creator: Dvidia
License: https://owterminal.com/cite

One quoted capture. Rank only lives inside a filter.

Qwen3.6-35B-A3B

M4 Pro 64GB · 4-bit · Rapid-MLX

Decode · tok/s

108.6

Prefill

—

tok/100W

241.3

Qwen3.6-35B-A3B (4-bit, ~3B active, Rapid-MLX) vs. Nemotron 3.5 Lightning 30B-A3B (4-bit, ~3–3.6B active, TensorFold) on M4 Pro 64GB. Qwen: 108.6 tok/s + 15/15 tools.

First-person M4 Pro 64GB. Rank is the quoted 108.6. Nemotron side has no tok/s in the quote.

Officialclaimed

@draslan_eth

Open pair