← Back to community benchmarks
Qwen3.5-35B-A3B-5bit
Performance
8k
tokens
812.9
PP tok/s
46.8
TG tok/s
10078
TTFT (ms)
24.4
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 697.4 | 53.7 | 24.1 GB | view |
| 4k | 808.4 | 51.4 | 24.2 GB | view |
| 8k | 812.9 | 46.8 | 24.4 GB | current |
| 16k | 768.4 | 40.6 | 24.9 GB | view |
| 32k | 703.9 | 32.2 | 25.7 GB | view |
| 64k | 559.4 | 20.6 | 27.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 53.7 | 1.00× |
| 2× | 84.4 | 1.57× |
| 4× | 124.1 | 2.31× |
| 8× | 159.6 | 2.97× |