← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
1k
tokens
1,242
PP tok/s
96.1
TG tok/s
824
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M5 Max (32c)
Memory
36 GB
GPU Cores
32
Software
oMLX
v0.3.9.dev2
macOS
macOS 26.5
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,242 | 96.1 | 14.3 GB | current |
| 4k | 2,196 | 92.9 | 14.9 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 96.1 | 1.00× |
| 2× | 146.5 | 1.52× |
| 4× | 196.5 | 2.04× |