← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-Opus-Distilled
Performance
4k
tokens
172.7
PP tok/s
27.0
TG tok/s
23713
TTFT (ms)
16.1
Peak mem (GB)
Hardware
Chip
M1 Ultra (64c)
Memory
128 GB
GPU Cores
64
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 164.5 | 28.8 | 15.8 GB | view |
| 4k | 172.7 | 27.0 | 16.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 28.8 | 1.00× |
| 2× | 36.5 | 1.27× |
| 4× | 42.0 | 1.46× |