← Back to community benchmarks
Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled
Performance
1k
tokens
371.0
PP tok/s
49.7
TG tok/s
2760
TTFT (ms)
27.3
Peak mem (GB)
Hardware
Chip
M1 Max (24c)
Memory
64 GB
GPU Cores
24
Software
oMLX
v0.3.6
macOS
macOS 15.7.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 371.0 | 49.7 | 27.3 GB | current |
| 4k | 437.7 | 46.9 | 28.1 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 49.7 | 1.00× |
| 2× | 63.6 | 1.28× |
| 4× | 127.5 | 2.57× |