← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
1,980
PP tok/s
102.3
TG tok/s
2069
TTFT (ms)
1.9
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,044 | 109.7 | 1.8 GB | view |
| 4k | 1,980 | 102.3 | 1.9 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 109.7 | 1.00× |
| 2× | 122.5 | 1.12× |
| 4× | 205.2 | 1.87× |