← Back to community benchmarks
Qwen3.5‑27B‑Claude‑Reasoning
Performance
1k
tokens
122.2
PP tok/s
15.6
TG tok/s
8378
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 122.2 | 15.6 | 15.8 GB | current |
| 4k | 125.9 | 15.2 | 16.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.6 | 1.00× |
| 2× | 29.7 | 1.90× |
| 4× | 32.4 | 2.08× |
| 8× | 32.2 | 2.06× |