← Back to community benchmarks
Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8
Performance
1k
tokens
310.5
PP tok/s
26.9
TG tok/s
3298
TTFT (ms)
9.6
Peak mem (GB)
Hardware
Chip
M4 Pro (16c)
Memory
24 GB
GPU Cores
16
Software
oMLX
v0.2.9
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 310.5 | 26.9 | 9.6 GB | current |
| 4k | 320.8 | 26.4 | 9.8 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 26.9 | 1.00× |
| 2× | 31.7 | 1.18× |
| 4× | 34.2 | 1.27× |