← Back to community benchmarks
Huihui-Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated
Performance
32k
tokens
3,155
PP tok/s
84.0
TG tok/s
10385
TTFT (ms)
38.9
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
32,768
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,476 | 98.1 | 35.4 GB | view |
| 4k | 3,192 | 91.6 | 36.2 GB | view |
| 8k | 3,843 | 95.1 | 36.7 GB | view |
| 16k | 3,624 | 90.5 | 37.4 GB | view |
| 32k | 3,155 | 84.0 | 38.9 GB | current |
| 64k | 2,248 | 70.5 | 41.9 GB | view |
| 128k | 1,268 | 49.0 | 47.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 98.1 | 1.00× |
| 2× | 145.5 | 1.48× |
| 4× | 208.5 | 2.13× |
| 8× | 249.6 | 2.54× |