← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
1,397
PP tok/s
203.0
TG tok/s
733
TTFT (ms)
1.7
Peak mem (GB)
Hardware
Chip
M2 Pro (19c)
Memory
16 GB
GPU Cores
19
Software
oMLX
v0.2.8
macOS
macOS 26.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,397 | 203.0 | 1.7 GB | current |
| 4k | 2,111 | 127.7 | 1.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 203.0 | 1.00× |
| 2× | 31.3 | 0.15× |
| 4× | 46.5 | 0.23× |