← Back to community benchmarks
Carnice-V2-27bmixed_3_6
Performance
1k
tokens
83.6
PP tok/s
13.6
TG tok/s
12246
TTFT (ms)
14.3
Peak mem (GB)
Hardware
Chip
M1 Max (32c)
Memory
64 GB
GPU Cores
32
Software
oMLX
v0.5.2rc1
macOS
macOS 26.5.2
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 83.6 | 13.6 | 14.3 GB | current |
| 16k | 77.4 | 12.1 | 16.8 GB | view |
| 64k | 62.0 | 9.6 | 22.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 13.6 | 1.00× |
| 2× | 15.6 | 1.15× |
| 4× | 17.7 | 1.30× |