← Back to community benchmarks
mxbai-rerank-large-v2
Performance
64k
tokens
1,840
PP tok/s
68.9
TG tok/s
35620
TTFT (ms)
5.3
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,395 | 152.3 | 3.4 GB | view |
| 4k | 3,746 | 137.7 | 3.5 GB | view |
| 8k | 4,349 | 122.4 | 3.6 GB | view |
| 16k | 3,729 | 103.4 | 3.9 GB | view |
| 32k | 2,807 | 85.0 | 4.4 GB | view |
| 64k | 1,840 | 68.9 | 5.3 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 152.3 | 1.00× |
| 2× | 143.4 | 0.94× |
| 4× | 276.4 | 1.81× |
| 8× | 513.5 | 3.37× |