← Back to community benchmarks
UI-TARS-1.5-7B
Performance
4k
tokens
253.2
PP tok/s
21.9
TG tok/s
16179
TTFT (ms)
5.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 260.2 | 23.1 | 5.2 GB | view |
| 4k | 253.2 | 21.9 | 5.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 23.1 | 1.00× |
| 2× | 34.0 | 1.47× |
| 4× | 46.4 | 2.01× |