SenseNova U1 8B MoT SFT needs about 7.6 GB of memory at Q4_K_M (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 7.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.6 GB.
SenseNova U1 8B MoT SFT – multimodal LLM with 9.35B parameters
SenseNova U1 8B MoT SFT is a 9.35B parameter multimodal model. It supports coding, reasoning, and tool use. The model is released under the Apache‑2.0 license and trained on 262144 context tokens.
Good at
- Coding tasks
- Reasoning problems
- Tool integration
Limits
- No vision support in this variant
- Large VRAM requirement for full precision
- Requires 262144 token context
Best for
- Developers building multimodal assistants
- Researchers testing multimodal reasoning
- Tool‑enabled code generation
Who it’s for. This model is intended for developers and researchers who need a multimodal foundation model with strong reasoning and coding capabilities. It is suitable for building assistants that interact with code and tools.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 1.9 GB | Fits | Get file → | |
| IQ1_S | 2.4 GB | 4.3 GB | Fits | Get file → | |
| IQ1_M | 2.5 GB | 4.4 GB | Fits | Get file → | |
| IQ2_XXS | 2.8 GB | 4.7 GB | Fits | Get file → | |
| IQ2_XS | 3.0 GB | 4.9 GB | Fits | Get file → | |
| IQ2_S | 3.2 GB | 5.1 GB | Fits | Get file → | |
| IQ2_M | 3.4 GB | 5.4 GB | Fits | Get file → | |
| Q2_K_S | 3.5 GB | 5.4 GB | Fits | Get file → | |
| Q2_K | 3.7 GB | 5.6 GB | Fits | Get file → | |
| IQ3_XXS | 3.8 GB | 5.7 GB | Fits | Get file → | |
| IQ3_XS | 4.1 GB | 6.0 GB | Fits | Get file → | |
| Q3_K_S | 4.3 GB | 6.2 GB | Fits | Get file → | |
| IQ3_S | 4.3 GB | 6.2 GB | Fits | Get file → | |
| IQ3_M | 4.4 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_M | 4.7 GB | 6.6 GB | Fits | Get file → | |
| Q3_K_L | 5.0 GB | 6.9 GB | Fits | Get file → | |
| IQ4_XS | 5.2 GB | 7.1 GB | Fits | Get file → | |
| Q4_0 | 5.4 GB | 7.4 GB | Tight | Get file → | |
| IQ4_NL | 5.4 GB | 7.4 GB | Tight | Get file → | |
| Q4_K_S | 5.5 GB | 7.4 GB | Tight | Get file → | |
| Q4_K_M | 5.7 GB | 7.6 GB | Tight | Get file → | |
| Q4_1 | 6.0 GB | 7.9 GB | Tight | Get file → | |
| Q5_K_S | 6.5 GB | 8.4 GB | Too big | Get file → | |
| Q5_K_M | 6.7 GB | 8.6 GB | Too big | Get file → | |
| Q6_K | 7.7 GB | 9.6 GB | Too big | Get file → |
For 8 GB VRAM use the Q4_K_M quant (file size 5.72 GB, estimated 7.6 GB memory at 8 k context). For 12 GB VRAM the Q5_K_M quant (6.67 GB, 8.6 GB memory) is a good balance. The smallest quant, IQ1_S, uses 2.36 GB and 4.3 GB memory, suitable for 4 GB VRAM setups.
What GPU do you need for SenseNova U1 8B MoT SFT?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 1.9 GB in use).
- 6 GB VRAM: the best quant that fits is IQ3_XS (4.1 GB file, about 6.0 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_1 (6.0 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (7.7 GB file, about 9.6 GB in use).
Which SenseNova U1 8B MoT SFT quant should you choose?
Q4_K_M is the usual starting point for SenseNova U1 8B MoT SFT: it balances file size and quality well. Here it is a 5.7 GB file.
If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about SenseNova U1 8B MoT SFT
How much VRAM does SenseNova U1 8B MoT SFT need?
About 7.6 GB at Q4_K_M with an 8K context window. That is the 5.7 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run SenseNova U1 8B MoT SFT on an 8 GB GPU?
Yes, with Q4_1: the 6.0 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of SenseNova U1 8B MoT SFT GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 2.4 GB, IQ1_M is 2.5 GB, IQ2_XXS is 2.8 GB, IQ2_XS is 3.0 GB, IQ2_S is 3.2 GB and 19 more.
What context length does SenseNova U1 8B MoT SFT support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.4 GB at 8K and 5.6 GB at 32K.
Where can I download SenseNova U1 8B MoT SFT GGUF?
The files are on Hugging Face in the mradermacher/SenseNova-U1-8B-MoT-SFT-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does SenseNova U1 8B MoT SFT use?
Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run SenseNova U1 8B MoT SFT on 8 GB VRAM?
Yes, use the Q4_K_M quant which requires approximately 7.6 GB memory at 8 k context.
Does this model support vision tasks?
No, this variant does not include vision support.
What license applies to this model?
The model is released under the Apache‑2.0 license.