← Back to community benchmarks
Qwen3.6-27B-oQ4
Performance
8k
tokens
173.0
PP tok/s
18.3
TG tok/s
47344
TTFT (ms)
18.5
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
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 194.3 | 21.0 | 16.4 GB | view |
| 4k | 194.0 | 19.3 | 17.9 GB | view |
| 8k | 173.0 | 18.3 | 18.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.0 | 1.00× |
| 2× | 32.4 | 1.54× |
| 4× | 36.2 | 1.72× |