← Back to community benchmarks
Huihui-Qwen3-VL-8B-Instruct-abliterated-q4
Performance
4k
tokens
215.1
PP tok/s
18.6
TG tok/s
19043
TTFT (ms)
6.4
Peak mem (GB)
Hardware
Chip
M4 (10c)
Memory
16 GB
GPU Cores
10
Software
oMLX
v0.2.6
macOS
macOS 26.3.1
Context
4,096
Performance by Context Length
| Context | PP tok/s | TG tok/s | Peak Mem | |
|---|---|---|---|---|
| 1k | 224.4 | 20.5 | 6.0 GB | view |
| 4k | 215.1 | 18.6 | 6.4 GB | current |
Batching Results
| Batch Size | TG tok/s | Speedup |
|---|---|---|
| 1× | 20.5 | 1.00× |
| 2× | 41.0 | 2.00× |
| 4× | 51.6 | 2.52× |