← Back to community benchmarks
Qwen3.5-2B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
1,059
PP tok/s
24.6
TG tok/s
3869
TTFT (ms)
4.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 860.0 | 25.1 | 4.1 GB | view |
| 4k | 1,059 | 24.6 | 4.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 25.1 | 1.00× |
| 2× | 32.0 | 1.27× |
| 4× | 62.2 | 2.48× |