← Back to community benchmarks

Qwen3-Coder-Next

M1 Max (32c) · 64 GB · 4bit · 2026-04-23
User comment+DFlash
Performance
16k
tokens
431.9
PP tok/s
33.7
TG tok/s
37931
TTFT (ms)
45.0
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.8.dev1
macOS macOS 26.3.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 159.6 45.0 44.0 GB view
16k 431.9 33.7 45.0 GB current
32k 390.4 26.5 46.4 GB view
64k 294.6 17.6 49.1 GB view