← Back to community benchmarks
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
Performance
4k
tokens
1,431
PP tok/s
67.9
TG tok/s
2862
TTFT (ms)
36.2
Peak mem (GB)
Hardware
Chip
M3 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.9rc1
macOS
macOS 15.7.5
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,029 | 70.5 | 35.4 GB | view |
| 4k | 1,431 | 67.9 | 36.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 70.5 | 1.00× |
| 2× | 118.9 | 1.69× |
| 4× | 168.5 | 2.39× |