← Back to community benchmarks
Qwen3.6-35B-A3B-Kimi-K2.6-Reasoning-Distilled-oQ8e
Performance
16k
tokens
1,133
PP tok/s
65.6
TG tok/s
14457
TTFT (ms)
37.4
Peak mem (GB)
Hardware
Chip
M2 Ultra (60c)
Memory
192 GB
GPU Cores
60
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 661.6 | 73.1 | 35.4 GB | view |
| 4k | 1,124 | 70.5 | 36.2 GB | view |
| 8k | 1,172 | 59.9 | 36.6 GB | view |
| 16k | 1,133 | 65.6 | 37.4 GB | current |
| 32k | 1,031 | 58.3 | 38.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 73.1 | 1.00× |
| 2× | 121.4 | 1.66× |
| 4× | 172.0 | 2.35× |