← Back to community benchmarks
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled
Performance
4k
tokens
393.0
PP tok/s
34.6
TG tok/s
10423
TTFT (ms)
3.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 378.5 | 36.2 | 3.3 GB | view |
| 4k | 393.0 | 34.6 | 3.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 36.2 | 1.00× |
| 2× | 69.0 | 1.91× |
| 4× | 88.7 | 2.45× |