← Back to community benchmarks
Qwen3-Coder-Next-oQ8
Performance
195k
tokens
845.4
PP tok/s
36.7
TG tok/s
236572
TTFT (ms)
97.8
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
200,000
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,947 | 76.4 | 80.2 GB | view |
| 195k | 845.4 | 36.7 | 97.8 GB | current |