← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
4,259
PP tok/s
196.9
TG tok/s
962
TTFT (ms)
2.2
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.2.6
macOS
macOS 15.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 4,364 | 208.7 | 2.0 GB | view |
| 4k | 4,259 | 196.9 | 2.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 208.7 | 1.00× |
| 2× | 381.8 | 1.83× |
| 4× | 567.3 | 2.72× |