← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
1,993
PP tok/s
90.9
TG tok/s
514
TTFT (ms)
1.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,993 | 90.9 | 1.8 GB | current |
| 4k | 1,933 | 83.7 | 2.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 90.9 | 1.00× |
| 2× | 170.8 | 1.88× |
| 4× | 278.1 | 3.06× |