← Back to community benchmarks

Qwen3-VL-8B-Instruct

M4 (10c) · 32 GB · 8bit · 2026-03-10
Performance
4k
tokens
198.4
PP tok/s
9.9
TG tok/s
20649
TTFT (ms)
10.3
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 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 217.2 11.3 9.7 GB view
4k 198.4 9.9 10.3 GB current
8k 183.1 8.9 10.8 GB view
16k 159.8 7.2 11.9 GB view
Batching Results
Batch Size TG tok/s Speedup
11.3 1.00×
20.9 1.85×
33.3 2.95×
34.6 3.06×