← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
1,360
PP tok/s
13.0
TG tok/s
3011
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M4 (8c)
Memory
16 GB
GPU Cores
8
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 | 1,141 | 13.2 | 3.3 GB | view |
| 4k | 1,360 | 13.0 | 3.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.2 | 1.00× |
| 2× | 23.6 | 1.79× |
| 4× | 46.4 | 3.52× |
| 8× | 89.3 | 6.77× |