← Back to community benchmarks
Qwen3.5-0.8B
Performance
1k
tokens
2,333
PP tok/s
164.7
TG tok/s
439
TTFT (ms)
1.5
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,333 | 164.7 | 1.5 GB | current |
| 4k | 2,234 | 155.4 | 1.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 164.7 | 1.00× |
| 2× | 313.6 | 1.90× |
| 4× | 428.9 | 2.60× |