← Back to community benchmarks
InternVL3-38B
Performance
4k
tokens
256.5
PP tok/s
17.9
TG tok/s
15971
TTFT (ms)
44.6
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
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 255.4 | 18.9 | 43.5 GB | view |
| 4k | 256.5 | 17.9 | 44.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 18.9 | 1.00× |
| 2× | 16.6 | 0.88× |
| 4× | 17.5 | 0.93× |