← Back to community benchmarks
gemma-4-E4B-it-The-DECKARD-Expresso-Universe-HERETIC-UNCENSORED-Thinking-mxfp8
Performance
4k
tokens
228.9
PP tok/s
10.6
TG tok/s
17895
TTFT (ms)
8.8
Peak mem (GB)
Hardware
Chip
M1 (8c)
Memory
16 GB
GPU Cores
8
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 218.9 | 11.4 | 8.7 GB | view |
| 4k | 228.9 | 10.6 | 8.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 11.4 | 1.00× |
| 2× | 21.2 | 1.86× |
| 4× | 28.1 | 2.46× |