← Back to community benchmarks
Qwen3.5-0.8B9bit
Performance
64k
tokens
4,818
PP tok/s
122.4
TG tok/s
13604
TTFT (ms)
4.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,898 | 301.0 | 1.9 GB | view |
| 64k | 4,818 | 122.4 | 4.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 301.0 | 1.00× |
| 2× | 508.5 | 1.69× |
| 4× | 745.7 | 2.48× |
| 8× | 1070.8 | 3.56× |