← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
2,150
PP tok/s
178.0
TG tok/s
476
TTFT (ms)
1.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,150 | 178.0 | 1.5 GB | current |
| 4k | 2,147 | 166.4 | 1.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 178.0 | 1.00× |
| 2× | 315.4 | 1.77× |
| 4× | 412.8 | 2.32× |