← Back to community benchmarks
Qwen3.5-27B
Performance
64k
tokens
333.7
PP tok/s
15.0
TG tok/s
196406
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 413.0 | 21.6 | 29.1 GB | view |
| 4k | 421.8 | 21.0 | 29.5 GB | view |
| 8k | 417.0 | 20.4 | 29.9 GB | view |
| 32k | 378.9 | 17.3 | 32.6 GB | view |
| 64k | 333.7 | 15.0 | 36.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.6 | 1.00× |
| 2× | 38.2 | 1.77× |
| 4× | 56.9 | 2.63× |
| 8× | 70.0 | 3.24× |