← Back to community benchmarks
Qwen3.5-9B-GLM5.1-Distill-v1
Performance
1k
tokens
202.1
PP tok/s
9.8
TG tok/s
5068
TTFT (ms)
9.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
32 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 202.1 | 9.8 | 9.8 GB | current |
| 4k | 201.8 | 10.6 | 10.4 GB | view |
| 8k | 204.4 | 10.8 | 10.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 9.8 | 1.00× |
| 2× | 22.5 | 2.30× |
| 4× | 45.9 | 4.68× |
| 8× | 89.5 | 9.13× |