← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
3,212
PP tok/s
200.2
TG tok/s
319
TTFT (ms)
1.7
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.2.7
macOS
macOS 26.4
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 3,212 | 200.2 | 1.7 GB | current |
| 4k | 3,132 | 211.4 | 1.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 200.2 | 1.00× |
| 2× | 353.2 | 1.76× |
| 4× | 467.7 | 2.34× |