← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
245.0
PP tok/s
19.1
TG tok/s
16720
TTFT (ms)
23.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.2.11
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 239.3 | 20.7 | 22.9 GB | view |
| 4k | 245.0 | 19.1 | 23.2 GB | current |
| 8k | 241.5 | 19.5 | 23.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.7 | 1.00× |
| 2× | 33.4 | 1.61× |
| 4× | 36.0 | 1.74× |