← Back to community benchmarks
gemma-4-26B-A4B-itmxfp8
Performance
1k
tokens
2,210
PP tok/s
62.3
TG tok/s
463
TTFT (ms)
26.1
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.1
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,210 | 62.3 | 26.1 GB | current |
| 4k | 2,978 | 60.1 | 26.6 GB | view |
| 8k | 3,711 | 46.0 | 26.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 62.3 | 1.00× |
| 2× | 65.0 | 1.04× |
| 4× | 106.5 | 1.71× |