← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
773.5
PP tok/s
7.6
TG tok/s
5295
TTFT (ms)
3.4
Peak mem (GB)
Hardware
Chip
M1 (7c)
Memory
16 GB
GPU Cores
7
Software
oMLX
v0.2.7
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 681.6 | 7.3 | 3.3 GB | view |
| 4k | 773.5 | 7.6 | 3.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 7.3 | 1.00× |
| 2× | 14.1 | 1.93× |
| 4× | 26.1 | 3.58× |