← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8
Performance
4k
tokens
904.9
PP tok/s
56.0
TG tok/s
4526
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M4 Pro (20c)
Memory
64 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 | 774.9 | 58.5 | 35.4 GB | view |
| 4k | 904.9 | 56.0 | 36.2 GB | current |
| 8k | 888.4 | 53.7 | 36.5 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 58.5 | 1.00× |
| 2× | 89.2 | 1.52× |
| 4× | 177.8 | 3.04× |