← Back to community benchmarks
Qwen3.5-27B
Performance
1k
tokens
164.3
PP tok/s
17.5
TG tok/s
6232
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip
M3 Max (30c)
Memory
36 GB
GPU Cores
30
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 164.3 | 17.5 | 16.6 GB | current |
| 4k | 153.5 | 15.2 | 17.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 17.5 | 1.00× |
| 2× | 29.2 | 1.67× |
| 4× | 32.5 | 1.86× |
| 8× | 19.4 | 1.11× |