← Back to community benchmarks
qwen3.5-9bmxfp8
Performance
1k
tokens
1,069
PP tok/s
62.7
TG tok/s
958
TTFT (ms)
11.5
Peak mem (GB)
Hardware
Chip
M2 Ultra (76c)
Memory
192 GB
GPU Cores
76
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,069 | 62.7 | 11.5 GB | current |
| 8k | 1,080 | 57.4 | 12.4 GB | view |
| 16k | 1,042 | 51.3 | 13.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.7 | 1.00× |
| 2× | 96.4 | 1.54× |
| 4× | 110.6 | 1.76× |