← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
3,829
PP tok/s
233.1
TG tok/s
1070
TTFT (ms)
2.1
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,580 | 265.8 | 1.9 GB | view |
| 4k | 3,829 | 233.1 | 2.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 265.8 | 1.00× |
| 2× | 516.6 | 1.94× |
| 4× | 686.1 | 2.58× |
| 8× | 881.8 | 3.32× |