← Back to community benchmarks
Qwen3.5-0.8B
Performance
8k
tokens
1,609
PP tok/s
12.2
TG tok/s
5090
TTFT (ms)
3.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.0.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,379 | 12.7 | 3.3 GB | view |
| 4k | 1,597 | 12.7 | 3.4 GB | view |
| 8k | 1,609 | 12.2 | 3.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.7 | 1.00× |
| 2× | 24.9 | 1.96× |
| 4× | 48.0 | 3.78× |