← Back to community benchmarks
Mistral-7B-Instruct-v0.3
Performance
4k
tokens
230.0
PP tok/s
20.0
TG tok/s
17811
TTFT (ms)
4.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.8rc1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 239.2 | 22.7 | 4.5 GB | view |
| 4k | 230.0 | 20.0 | 4.8 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 22.7 | 1.00× |
| 2× | 44.5 | 1.96× |
| 4× | 55.5 | 2.44× |