← Back to community benchmarks
Qwen3.5-122B-A10B-5bit
Performance
1k
tokens
1,175
PP tok/s
47.7
TG tok/s
871
TTFT (ms)
84.2
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.2.24.dev2
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,175 | 47.7 | 84.2 GB | current |
| 4k | 1,485 | 45.5 | 85.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.7 | 1.00× |
| 2× | 68.6 | 1.44× |
| 4× | 84.4 | 1.77× |