← Back to community benchmarks

Qwen3-Coder-Next

M1 Max (32c) · 64 GB · 4bit · 2026-04-23
User comment+DFlash
Performance
4k
tokens
159.6
PP tok/s
45.0
TG tok/s
25659
TTFT (ms)
44.0
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
4k 159.6 45.0 44.0 GB current
16k 431.9 33.7 45.0 GB view
32k 390.4 26.5 46.4 GB view
64k 294.6 17.6 49.1 GB view