← Back to community benchmarks
gemma-4-26B-A4B-it-heretic-msq-2.6bit
Performance
1k
tokens
454.1
PP tok/s
54.0
TG tok/s
2255
TTFT (ms)
9.2
Peak mem (GB)
Hardware
Chip
M2 Max (30c)
Memory
32 GB
GPU Cores
30
Software
oMLX
v0.3.5
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 454.1 | 54.0 | 9.2 GB | current |
| 4k | 492.7 | 46.6 | 9.7 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 54.0 | 1.00× |
| 2× | 68.3 | 1.26× |
| 4× | 81.1 | 1.50× |