← Back to community benchmarks
Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2
Performance
1k
tokens
377.2
PP tok/s
38.0
TG tok/s
2715
TTFT (ms)
3.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.19
macOS
macOS 26.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 377.2 | 38.0 | 3.3 GB | current |
| 4k | 393.1 | 36.3 | 4.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 38.0 | 1.00× |
| 2× | 72.0 | 1.89× |
| 4× | 86.8 | 2.28× |