← Back to community benchmarks
Jundot-Qwen3.6-27B-oQ8-mtp
Performance
4k
tokens
407.5
PP tok/s
30.5
TG tok/s
10051
TTFT (ms)
30.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.9
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 376.0 | 30.1 | 28.8 GB | view |
| 4k | 407.5 | 30.5 | 30.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 30.1 | 1.00× |
| 2× | 36.8 | 1.22× |
| 4× | 56.0 | 1.86× |