← Back to community benchmarks
Qwen3.5-27B-Claude-4.6-OS-INSTRUCT-mxfp8
Performance
1k
tokens
303.5
PP tok/s
22.3
TG tok/s
3374
TTFT (ms)
28.4
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
256 GB
GPU Cores
60
Software
oMLX
v0.2.10
macOS
macOS 15.6
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 303.5 | 22.3 | 28.4 GB | current |
| 4k | 307.5 | 21.6 | 28.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.3 | 1.00× |
| 2× | 27.1 | 1.22× |
| 4× | 32.1 | 1.44× |