← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
242.0
PP tok/s
27.7
TG tok/s
16925
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 238.8 | 29.0 | 15.8 GB | view |
| 4k | 242.0 | 27.7 | 16.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 29.0 | 1.00× |
| 2× | 53.3 | 1.84× |
| 4× | 60.2 | 2.08× |