← Back to community benchmarks
InternVL3-38B
Performance
1k
tokens
255.9
PP tok/s
19.0
TG tok/s
4002
TTFT (ms)
43.5
Peak mem (GB)
Hardware
Chip
M3 Ultra (60c)
Memory
96 GB
GPU Cores
60
Software
oMLX
v0.2.7
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 255.9 | 19.0 | 43.5 GB | current |
| 4k | 256.1 | 17.9 | 44.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 19.0 | 1.00× |
| 2× | 19.1 | 1.01× |
| 4× | 33.8 | 1.78× |