← Back to community benchmarks
nightmedia-Qwen3-Coder-Next-mxfp8
Performance
1k
tokens
1,054
PP tok/s
67.2
TG tok/s
972
TTFT (ms)
77.8
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,054 | 67.2 | 77.8 GB | current |
| 4k | 1,257 | 64.6 | 78.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 67.2 | 1.00× |
| 2× | 99.3 | 1.48× |
| 4× | 129.9 | 1.93× |