← Back to community benchmarks
Qwen3.5-0.8B
Performance
8k
tokens
3,073
PP tok/s
39.8
TG tok/s
2666
TTFT (ms)
3.8
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
32 GB
GPU Cores
24
Software
oMLX
v0.2.6
macOS
macOS 26.2
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,964 | 41.1 | 3.5 GB | view |
| 4k | 2,562 | 40.4 | 3.8 GB | view |
| 8k | 3,073 | 39.8 | 3.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 41.1 | 1.00× |
| 2× | 43.0 | 1.05× |
| 4× | 54.6 | 1.33× |