← Back to community benchmarks
granite-4.0-h-tiny-oQ8e
Performance
4k
tokens
1,418
PP tok/s
92.8
TG tok/s
2889
TTFT (ms)
10.2
Peak mem (GB)
Hardware
Chip
M1 Ultra (48c)
Memory
64 GB
GPU Cores
48
Software
oMLX
v0.3.6
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 954.3 | 96.2 | 9.1 GB | view |
| 4k | 1,418 | 92.8 | 10.2 GB | current |
| 8k | 1,480 | 90.1 | 10.2 GB | view |
| 16k | 1,460 | 82.1 | 10.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.2 | 1.00× |
| 2× | 166.1 | 1.73× |
| 4× | 244.1 | 2.54× |
| 8× | 327.0 | 3.40× |