← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-mxfp8
Performance
4k
tokens
178.7
PP tok/s
11.2
TG tok/s
22925
TTFT (ms)
10.6
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
24 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 185.5 | 12.3 | 10.3 GB | view |
| 4k | 178.7 | 11.2 | 10.6 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 12.3 | 1.00× |
| 2× | 17.4 | 1.41× |
| 4× | 13.9 | 1.13× |