← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSOREDmxfp8
Performance
4k
tokens
637.7
PP tok/s
14.7
TG tok/s
6423
TTFT (ms)
10.2
Peak mem (GB)
Hardware
Chip
M5 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.5.dev1
macOS
macOS 26.4.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 554.2 | 14.7 | 9.5 GB | view |
| 4k | 637.7 | 14.7 | 10.2 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 14.7 | 1.00× |
| 2× | 31.2 | 2.12× |
| 4× | 35.1 | 2.39× |