Skip to content

SenseNova-U1.5-8B-MoT-8step-4bit

mlx-community/SenseNova-U1.5-8B-MoT-8step-4bit
Any to any · mlx
4-bit Open on Hugging Face
Parameters
18B
Weights (est.)
≈ 11.8 GB
Mac memory (est.)
16 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
sensenova/SenseNova-U1.5-8B-MoT (finetune)
Vendor
sensenova
Task
Any to any
Quantisation
4-bit
Licence
apache-2.0
Downloads
337 in the last 30 days · 924 all time · 3 likes
Published
2026-08-24 · updated 2026-10-11 (1mo ago)
Tags
neo_chat, mlx-swift, image-generation, image-editing, native multimodal, distilled, custom_code

Other MLX builds of sensenova/SenseNova-U1.5-8B-MoT

Build Quantisation Weights Mac memory Downloads
SenseNova-U1.5-8B-MoT-8step-4bit (this one) 4-bit ≈ 11.8 GB 16 GB+ 337
SenseNova-U1.5-8B-MoT-8step-v2-4bit 4-bit ≈ 11.8 GB 16 GB+ 105
SenseNova-U1.5-8B-MoT-8step-v2-8bit 8-bit ≈ 19.9 GB 32 GB+ 82
SenseNova-U1.5-8B-MoT-8bit 8-bit ≈ 19.9 GB 32 GB+ 64
SenseNova-U1.5-8B-MoT-8step-8bit 8-bit ≈ 19.9 GB 32 GB+ 56
SenseNova-U1.5-8B-MoT-pose-8bit 8-bit ≈ 19.9 GB 32 GB+ 19
SenseNova-U1.5-8B-MoT-bf16 bf16 ≈ 35.1 GB 48 GB+ 41
SenseNova-U1.5-8B-MoT-pose-bf16 bf16 ≈ 35.1 GB 48 GB+ 16