← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
1,954
PP tok/s
109.3
TG tok/s
524
TTFT (ms)
1.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 15.7.3
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,954 | 109.3 | 1.8 GB | current |
| 4k | 1,995 | 104.1 | 1.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 109.3 | 1.00× |
| 2× | 203.2 | 1.86× |
| 4× | 307.9 | 2.82× |
| 8× | 306.5 | 2.80× |