← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
2,419
PP tok/s
61.2
TG tok/s
423
TTFT (ms)
2.3
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,419 | 61.2 | 2.3 GB | current |
| 4k | 2,437 | 59.0 | 2.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 61.2 | 1.00× |
| 2× | 71.8 | 1.17× |
| 4× | 137.5 | 2.25× |