← Back to community benchmarks
Qwen3.5-122B-A10BQ3-VL-convert
Performance
1k
tokens
217.5
PP tok/s
39.0
TG tok/s
4707
TTFT (ms)
52.2
Peak mem (GB)
Hardware
Chip
M2 Max (38c)
Memory
96 GB
GPU Cores
38
Software
oMLX
v0.2.13
macOS
macOS 15.7.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 217.5 | 39.0 | 52.2 GB | current |
| 4k | 231.1 | 36.2 | 52.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 39.0 | 1.00× |
| 2× | 47.9 | 1.23× |
| 4× | 95.6 | 2.45× |