← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8
Performance
1k
tokens
1,565
PP tok/s
97.5
TG tok/s
654
TTFT (ms)
35.4
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,565 | 97.5 | 35.4 GB | current |
| 4k | 3,472 | 95.9 | 36.2 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 97.5 | 1.00× |
| 2× | 150.1 | 1.54× |
| 4× | 232.7 | 2.39× |
| 8× | 318.3 | 3.26× |