Skip to content

Lance-3B-Video-bf16

mlx-community/Lance-3B-Video-bf16
bf16 Open on Hugging Face
Parameters
6.4B
Weights (est.)
≈ 12.9 GB
Mac memory (est.)
24 GB+

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Details

Base model
bytedance-research/Lance (finetune)
Vendor
bytedance-research
Task
Text to video
Quantisation
bf16
Licence
apache-2.0
Downloads
766 in the last 30 days · 5.4K all time · 10 likes
Published
2026-05-21 · updated 2026-06-05 (5mo ago)
Languages
en, zh
Tags
qwen2_5_vl, apple-silicon, lance, bytedance, multimodal, video-understanding, qwen2.5-vl, alpha

Other MLX builds of bytedance-research/Lance

Build Quantisation Weights Mac memory Downloads
Lance-3B-AWQ-INT4 4-bit ≈ 3.5 GB 8 GB+ 25
Lance-3B-8bit 8-bit ≈ 6.6 GB 16 GB+ 41
Lance-3B-bf16 bf16 ≈ 12.4 GB 16 GB+ 49
Lance-3B-Video-bf16 (this one) bf16 ≈ 12.9 GB 24 GB+ 766
Wan2.2-VAE-Lance-bf16 bf16 — — 0