← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
Performance
4k
tokens
776.9
PP tok/s
62.7
TG tok/s
5272
TTFT (ms)
20.9
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.9.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 662.5 | 64.9 | 20.2 GB | view |
| 4k | 776.9 | 62.7 | 20.9 GB | current |
| 8k | 771.4 | 60.9 | 21.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 64.9 | 1.00× |
| 2× | 102.8 | 1.58× |