← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
4k
tokens
1,896
PP tok/s
85.1
TG tok/s
2160
TTFT (ms)
14.7
Peak mem (GB)
Hardware
Chip
M3 Ultra (80c)
Memory
512 GB
GPU Cores
80
Software
oMLX
v0.3.4
macOS
macOS 26.2
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,465 | 91.0 | 14.2 GB | view |
| 4k | 1,896 | 85.1 | 14.7 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 91.0 | 1.00× |
| 2× | 145.7 | 1.60× |
| 4× | 212.6 | 2.34× |