← Back to community benchmarks
Qwen3.6-27B-oQ4-fp16-mtp
Performance
1k
tokens
257.9
PP tok/s
28.0
TG tok/s
3971
TTFT (ms)
16.4
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 257.9 | 28.0 | 16.4 GB | current |
| 4k | 267.2 | 27.0 | 17.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.0 | 1.00× |
| 2× | 49.5 | 1.77× |
| 4× | 56.0 | 2.00× |