← Back to community benchmarks
Qwen3.6-27B-oQ4-mtp
Performance
8k
tokens
131.4
PP tok/s
19.7
TG tok/s
62354
TTFT (ms)
19.2
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.3.9
macOS
macOS 26.4.1
Context
8,192
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 124.9 | 20.5 | 16.7 GB | view |
| 4k | 131.4 | 20.6 | 18.1 GB | view |
| 8k | 131.4 | 19.7 | 19.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 28.7 | 1.40× |
| 4× | 31.5 | 1.54× |