← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSOREDmxfp8
Performance
1k
tokens
215.5
PP tok/s
12.0
TG tok/s
4751
TTFT (ms)
10.0
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.8
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 215.5 | 12.0 | 10.0 GB | current |
| 4k | 219.7 | 11.9 | 10.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.0 | 1.00× |
| 2× | 22.7 | 1.89× |
| 4× | 23.3 | 1.94× |