← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
1,528
PP tok/s
12.8
TG tok/s
2681
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,334 | 13.0 | 3.3 GB | view |
| 4k | 1,528 | 12.8 | 3.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.0 | 1.00× |
| 2× | 23.4 | 1.80× |
| 4× | 17.6 | 1.35× |