← Back to community benchmarks
Qwen3-Coder-Next-mxfp4
Performance
4k
tokens
864.7
PP tok/s
45.8
TG tok/s
4737
TTFT (ms)
41.6
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
64 GB
GPU Cores
64
Software
oMLX
v0.3.5.dev1
macOS
macOS 15.7.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 687.9 | 47.1 | 40.8 GB | view |
| 4k | 864.7 | 45.8 | 41.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.1 | 1.00× |
| 2× | 78.8 | 1.67× |
| 4× | 117.2 | 2.49× |