← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
1k
tokens
128.6
PP tok/s
24.7
TG tok/s
7960
TTFT (ms)
15.8
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 128.6 | 24.7 | 15.8 GB | current |
| 4k | 133.5 | 23.0 | 16.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 24.7 | 1.00× |
| 2× | 29.8 | 1.21× |
| 4× | 33.2 | 1.34× |