Sabi Noema IQ3 S GSQ RCO needs about 1.8 GB of memory at Q4_0 (a 1.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 1.1 GB (Q4_0) to 11.8 GB (IQ3_S). Longer context needs more: at 32K tokens the KV cache alone adds about 0.7 GB.
26.9B‑parameter Sabi Noema IQ3 S GSQ RCO model
Sabi Noema IQ3 S GSQ RCO is a 26.9B‑parameter model built on the dflash architecture. It supports reasoning, tools, and vision. The model is released under the Apache‑2.0 license.
Good at
- Reasoning
- Tool usage
- Vision tasks
Limits
- No vision support beyond bundled mmproj
- Large VRAM requirement for higher context
- No mixture of experts
Best for
- Agentic applications
- Long‑form reasoning
- Vision‑enabled workflows
Who it’s for. Developers building agentic systems that require reasoning, tool use, and vision. The model is suitable for users with sufficient GPU memory to run the larger quantizations.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 1.1 GB | 1.8 GB | Fits | Get file → | |
| IQ3_S | 11.8 GB | 12.4 GB | Too big | Get file → |
For 8 GB VRAM, use the Q4_0 quant file (1.09 GB, 1.8 GB memory at 8 k context). For 12 GB VRAM, the IQ3_S quant file (11.77 GB, 12.4 GB memory at 8 k context) is recommended. Memory estimates are approximate.
What GPU do you need for Sabi Noema IQ3 S GSQ RCO?
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 Q4_0 (1.1 GB file, about 1.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_0 (1.1 GB file, about 1.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q4_0 (1.1 GB file, about 1.8 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (1.1 GB file, about 1.8 GB in use).
- 16 GB VRAM: the best quant that fits is IQ3_S (11.8 GB file, about 12.4 GB in use).
Which Sabi Noema IQ3 S GSQ RCO quant should you choose?
Q4_0 (1.1 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Sabi Noema IQ3 S GSQ RCO
How much VRAM does Sabi Noema IQ3 S GSQ RCO need?
About 1.8 GB at Q4_0 with an 8K context window. That is the 1.1 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 Sabi Noema IQ3 S GSQ RCO on an 8 GB GPU?
Yes, with Q4_0: the 1.1 GB file needs about 1.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Sabi Noema IQ3 S GSQ RCO GGUF?
It depends on the quant: Q4_0 is 1.1 GB, IQ3_S is 11.8 GB.
What context length does Sabi Noema IQ3 S GSQ RCO support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.7 GB at 32K.
Where can I download Sabi Noema IQ3 S GSQ RCO GGUF?
The files are on Hugging Face in the vmarcelo/Sabi-Noema-IQ3_S-GSQ-RCO-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 Sabi Noema IQ3 S GSQ RCO 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 this model on 8 GB VRAM?
Yes, using the Q4_0 quant file which is 1.09 GB and requires about 1.8 GB memory at 8 k context.
Does the model support vision?
Yes, it includes a bundled mmproj for vision tasks, but the main model does not have native vision support beyond that.
What license applies to this model?
The model is released under the Apache‑2.0 license.