← Back to community benchmarks
gemma-4-26B-A4B-it-Claude-Opus-Distilled-v24bit
Performance
1k
tokens
453.9
PP tok/s
51.8
TG tok/s
2256
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 453.9 | 51.8 | 14.3 GB | current |
| 4k | 493.6 | 49.3 | 14.8 GB | view |
| 8k | 506.1 | 47.2 | 15.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 51.8 | 1.00× |
| 2× | 69.0 | 1.33× |
| 4× | 81.6 | 1.58× |
| 8× | 94.9 | 1.83× |