← Back to community benchmarks
Carnice-9b
Performance
16k
tokens
585.1
PP tok/s
14.3
TG tok/s
28003
TTFT (ms)
7.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
16,384
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 211.2 | 21.7 | 6.1 GB | view |
| 4k | 222.7 | 21.2 | 6.7 GB | view |
| 8k | 212.1 | 19.1 | 7.1 GB | view |
| 16k | 585.1 | 14.3 | 7.8 GB | current |
| 32k | 526.8 | 14.4 | 8.6 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 21.7 | 1.00× |
| 2× | 40.2 | 1.85× |
| 4× | 48.1 | 2.22× |