← Back to community benchmarks
Qwen3.6-27BoQ4
Performance
4k
tokens
211.0
PP tok/s
20.2
TG tok/s
19414
TTFT (ms)
36.9
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.7
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 215.4 | 21.8 | 35.5 GB | view |
| 4k | 211.0 | 20.2 | 36.9 GB | current |
| 8k | 201.5 | 18.3 | 37.5 GB | view |
| 16k | 193.4 | 17.4 | 38.8 GB | view |
| 32k | 172.2 | 13.3 | 41.3 GB | view |
| 64k | 158.7 | 9.4 | 46.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.8 | 1.00× |
| 2× | 34.0 | 1.56× |
| 4× | 41.7 | 1.91× |