← Back to community benchmarks
Qwen3.5-35B-A3BIQ4_M
Performance
8k
tokens
739.6
PP tok/s
43.1
TG tok/s
11076
TTFT (ms)
23.3
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
48 GB
GPU Cores
16
Software
oMLX
v0.3.4
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 635.0 | 47.3 | 22.2 GB | view |
| 4k | 753.6 | 45.2 | 22.9 GB | view |
| 8k | 739.6 | 43.1 | 23.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 47.3 | 1.00× |
| 8× | 122.7 | 2.59× |