← Back to community benchmarks
Qwen3.5-9B-Gemini-3.1-Pro-Reasoning-Distill
Performance
4k
tokens
217.6
PP tok/s
15.5
TG tok/s
18823
TTFT (ms)
8.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 209.6 | 15.9 | 7.8 GB | view |
| 4k | 217.6 | 15.5 | 8.0 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.9 | 1.00× |
| 2× | 29.6 | 1.86× |
| 4× | 30.7 | 1.93× |
| 8× | 25.1 | 1.58× |