← Back to community benchmarks
gemma-4-26B-A4B-it-oQ8
Performance
16k
tokens
3,011
PP tok/s
68.7
TG tok/s
5442
TTFT (ms)
29.0
Peak mem (GB)
Hardware
Chip
M5 Max (40c)
Memory
128 GB
GPU Cores
40
Software
oMLX
v0.3.12
macOS
macOS 26.6
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 2,064 | 78.0 | 27.9 GB | view |
| 4k | 2,507 | 76.1 | 28.4 GB | view |
| 8k | 2,749 | 76.7 | 28.6 GB | view |
| 16k | 3,011 | 68.7 | 29.0 GB | current |
| 32k | 2,309 | 64.0 | 29.8 GB | view |
| 64k | 1,868 | 50.8 | 31.5 GB | view |
| 128k | 1,372 | 36.7 | 34.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 78.0 | 1.00× |
| 2× | 156.7 | 2.01× |
| 4× | 311.8 | 4.00× |