← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
127.3
PP tok/s
17.7
TG tok/s
32179
TTFT (ms)
22.4
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.2.10
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 124.8 | 18.4 | 22.0 GB | view |
| 4k | 127.3 | 17.7 | 22.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.4 | 1.00× |
| 2× | 22.7 | 1.23× |
| 4× | 24.9 | 1.35× |