← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
16k
tokens
175.2
PP tok/s
14.7
TG tok/s
93504
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 209.0 | 23.1 | 15.8 GB | view |
| 4k | 197.9 | 21.0 | 16.1 GB | view |
| 8k | 184.7 | 19.1 | 16.6 GB | view |
| 16k | 175.2 | 14.7 | 17.5 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.1 | 1.00× |
| 2× | 30.5 | 1.32× |
| 4× | 41.1 | 1.78× |
| 8× | 45.5 | 1.97× |