← Back to community benchmarks
Josiefied-Qwen3-8B-abliterated-v1
Performance
1k
tokens
217.1
PP tok/s
15.7
TG tok/s
4717
TTFT (ms)
6.8
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.3.5
macOS
macOS 26.3.1
Context
1,024
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 217.1 | 15.7 | 6.8 GB | current |
| 4k | 213.1 | 14.4 | 7.3 GB | view |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 15.7 | 1.00× |
| 2× | 29.9 | 1.90× |
| 4× | 31.2 | 1.99× |