← Back to community benchmarks
gemma-4-E4B-it-heretic-oQ6
Performance
64k
tokens
175.7
PP tok/s
10.9
TG tok/s
372963
TTFT (ms)
9.2
Peak mem (GB)
Hardware
Chip
M3 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
65,536
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 525.8 | 50.0 | 6.9 GB | view |
| 4k | 526.0 | 47.4 | 7.0 GB | view |
| 8k | 502.7 | 42.2 | 7.2 GB | view |
| 16k | 444.4 | 36.3 | 7.4 GB | view |
| 32k | 276.1 | 16.5 | 8.0 GB | view |
| 64k | 175.7 | 10.9 | 9.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 50.0 | 1.00× |
| 2× | 18.6 | 0.37× |
| 4× | 22.4 | 0.45× |