← Back to community benchmarks
Qwen3.5-27B
Performance
1k
tokens
101.3
PP tok/s
1.1
TG tok/s
10107
TTFT (ms)
56.9
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 101.3 | 1.1 | 56.9 GB | current |
| 4k | 124.2 | 1.1 | 57.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 1.1 | 1.00× |
| 2× | 1.5 | 1.36× |
| 4× | 2.7 | 2.45× |