← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
1,537
PP tok/s
12.3
TG tok/s
2665
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,329 | 12.1 | 3.3 GB | view |
| 4k | 1,537 | 12.3 | 3.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.1 | 1.00× |
| 2× | 24.3 | 2.01× |
| 4× | 48.1 | 3.98× |