← Back to community benchmarks
gemma-4-26b-a4b-it
Performance
16k
tokens
2,336
PP tok/s
63.9
TG tok/s
7015
TTFT (ms)
33.9
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.6
macOS
macOS 26.5
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,069 | 85.8 | 33.0 GB | view |
| 4k | 3,093 | 81.3 | 33.4 GB | view |
| 16k | 2,336 | 63.9 | 33.9 GB | current |
| 64k | 1,695 | 27.5 | 36.4 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 85.8 | 1.00× |
| 2× | 125.5 | 1.46× |
| 4× | 178.4 | 2.08× |