← Back to community benchmarks
Qwen3.5-27B-heretic
Performance
1k
tokens
80.5
PP tok/s
10.7
TG tok/s
12715
TTFT (ms)
29.1
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.8
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 80.5 | 10.7 | 29.1 GB | current |
| 4k | 70.6 | 9.5 | 29.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 10.7 | 1.00× |
| 2× | 11.3 | 1.06× |
| 4× | 12.2 | 1.14× |