← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning5bit
Performance
4k
tokens
2,021
PP tok/s
84.7
TG tok/s
2026
TTFT (ms)
24.1
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
48 GB
GPU Cores
20
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,201 | 88.2 | 23.3 GB | view |
| 4k | 2,021 | 84.7 | 24.1 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 88.2 | 1.00× |
| 2× | 132.1 | 1.50× |
| 4× | 163.9 | 1.86× |