← Back to community benchmarks
Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSOREDmxfp8
Performance
1k
tokens
1,168
PP tok/s
31.6
TG tok/s
877
TTFT (ms)
9.7
Peak mem (GB)
Hardware
Chip
M5 Pro (20c)
Memory
64 GB
GPU Cores
20
Software
oMLX
v0.3.8
macOS
macOS 26.4.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 1,168 | 31.6 | 9.7 GB | current |
| 4k | 1,435 | 31.1 | 10.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 31.6 | 1.00× |
| 2× | 57.6 | 1.82× |
| 4× | 75.9 | 2.40× |