← Back to community benchmarks
Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-Distilled-oQ8e
Performance
1k
tokens
2,237
PP tok/s
100.5
TG tok/s
458
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 | 2,237 | 100.5 | 35.4 GB | current |
| 4k | 3,749 | 97.8 | 36.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 100.5 | 1.00× |
| 2× | 154.9 | 1.54× |
| 4× | 227.0 | 2.26× |
| 8× | 313.6 | 3.12× |