← Back to community benchmarks
Qwen3.5-0.8B
Performance
4k
tokens
834.2
PP tok/s
56.6
TG tok/s
4910
TTFT (ms)
1.9
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
8 GB
GPU Cores
8
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 845.0 | 62.7 | 1.8 GB | view |
| 4k | 834.2 | 56.6 | 1.9 GB | current |
| 8k | 813.7 | 7.2 | 4.0 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.7 | 1.00× |
| 2× | 31.9 | 0.51× |
| 4× | 58.5 | 0.93× |