sensenova · First MLX build 24 Aug 2026
SenseNova-U1.5-8B-MoT
MLX
TextVisionAudio apache-2.0
A 18B parameter any to any model from sensenova, with 8 MLX builds, from 4-bit to bf16.
- Parameters
- 18B From Hugging Face
- Quantisation
- 4-bit SenseNova-U1.5-8B-MoT-8step-4bit
- Memory needed
- 16 GB Estimate, unified memory
- Download
- 11.8 GB Weights, estimated
- Downloads
- 350 This build, last 30 days
- Task
- Any to any Text, Vision, Audio
- MLX builds
- 8 On mlx-community
- Devices
- Mac Apple silicon
Memory
Will it fit?Needs about 16 GB at 4-bit
8 GB
16 GB
24 GB
32 GB
64 GB
128 GB
Fits with headroomTight, close other appsWon’t fit
Estimated from the size of the weights, plus a fifth for context and working memory and 2 GB for macOS and your apps. Long contexts need more.
Run it
Terminal · Hugging Face CLI$ pip install -U huggingface_hub
$ hf download mlx-community/SenseNova-U1.5-8B-MoT-8step-4bitMLX builds
8 on mlx-community| SenseNova-U1.5-8B-MoT-8step-4bit | 4-bit | 11.8 GB | 16 GB | 350 |
|---|---|---|---|---|
| SenseNova-U1.5-8B-MoT-8step-v2-4bit | 4-bit | 11.8 GB | 16 GB | 100 |
| SenseNova-U1.5-8B-MoT-8step-v2-8bit | 8-bit | 19.9 GB | 25 GB | 72 |
| SenseNova-U1.5-8B-MoT-8bit | 8-bit | 19.9 GB | 25 GB | 67 |
| SenseNova-U1.5-8B-MoT-8step-8bit | 8-bit | 19.9 GB | 25 GB | 54 |
| SenseNova-U1.5-8B-MoT-pose-8bit | 8-bit | 19.9 GB | 25 GB | 18 |
| SenseNova-U1.5-8B-MoT-bf16 | bf16 | 35.1 GB | 42 GB | 42 |
| SenseNova-U1.5-8B-MoT-pose-bf16 | bf16 | 35.1 GB | 42 GB | 15 |
Sizes are estimated from Hugging Face’s parameter counts and the quantisation. Downloads are for the last 30 days.