← Back to community benchmarks

Qwen3-Coder-Next

M1 Max (32c) · 64 GB · 4bit · 2026-04-23
User comment+DFlash
Performance
32k
tokens
390.4
PP tok/s
26.5
TG tok/s
83926
TTFT (ms)
46.4
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 32,768
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 view
32k 390.4 26.5 46.4 GB current
64k 294.6 17.6 49.1 GB view