← Back to community benchmarks
Qwen3.5-4B
Performance
4k
tokens
2,595
PP tok/s
104.1
TG tok/s
1578
TTFT (ms)
6.1
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
256 GB
GPU Cores
80
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 | 2,527 | 109.7 | 5.9 GB | view |
| 4k | 2,595 | 104.1 | 6.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 109.7 | 1.00× |
| 2× | 192.5 | 1.75× |
| 4× | 281.2 | 2.56× |
| 8× | 372.9 | 3.40× |