← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
128k
tokens
630.6
PP tok/s
36.3
TG tok/s
207855
TTFT (ms)
34.2
Peak mem (GB)
Hardware
Chip
M4 Max (40c)
Memory
64 GB
GPU Cores
40
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
131,072
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,168 | 78.2 | 25.8 GB | view |
| 4k | 1,391 | 75.9 | 26.3 GB | view |
| 8k | 1,370 | 72.7 | 26.8 GB | view |
| 16k | 1,308 | 68.5 | 27.1 GB | view |
| 32k | 1,070 | 60.5 | 28.0 GB | view |
| 64k | 928.6 | 50.1 | 30.0 GB | view |
| 128k | 630.6 | 36.3 | 34.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 78.2 | 1.00× |
| 2× | 117.4 | 1.50× |
| 4× | 160.0 | 2.05× |