Omni R1 Zero needs about 9.1 GB of memory at Q4_K_M (a 4.3 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 25 quants, from 0.0 GB to 5.8 GB (Q6_K).
Omni R1 Zero – 7.01B chameleon model focused on reasoning
Omni R1 Zero is a 7.01B parameter chameleon architecture model trained without multimodal annotations. It uses step‑wise visualizations from text‑only CoT seeds and follows the PeSFT+PeRPO recipe for interleaved multimodal reasoning. The model is released under the MIT license.
Good at
- Reasoning tasks
- Text‑only CoT bootstrapping
- Interleaved multimodal reasoning
Limits
- No vision support
- Limited context to 9900 tokens
- Requires 8k context for memory estimates
Best for
- Developing reasoning‑centric LLMs
- Testing step‑wise visualizations
- Fine‑tuning multimodal reasoning
Who it’s for. Researchers and developers building reasoning‑focused language models who need a lightweight, MIT‑licensed base. The model is suitable for those who prefer text‑only training pipelines and want to experiment with interleaved multimodal reasoning.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 4.8 GB | Fits | Get file → | |
| IQ1_S | 1.7 GB | 6.5 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 6.6 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 6.8 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 7.0 GB | Fits | Get file → | |
| IQ2_S | 2.4 GB | 7.1 GB | Fits | Get file → | |
| Q2_K_S | 2.5 GB | 7.3 GB | Tight | Get file → | |
| IQ2_M | 2.5 GB | 7.3 GB | Tight | Get file → | |
| Q2_K | 2.7 GB | 7.5 GB | Tight | Get file → | |
| IQ3_XXS | 2.7 GB | 7.5 GB | Tight | Get file → | |
| IQ3_XS | 3.0 GB | 7.8 GB | Tight | Get file → | |
| IQ3_S | 3.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K_S | 3.1 GB | 7.9 GB | Tight | Get file → | |
| IQ3_M | 3.3 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_M | 3.5 GB | 8.3 GB | Too big | Get file → | |
| Q3_K_L | 3.8 GB | 8.6 GB | Too big | Get file → | |
| IQ4_XS | 3.8 GB | 8.6 GB | Too big | Get file → | |
| IQ4_NL | 4.0 GB | 8.8 GB | Too big | Get file → | |
| Q4_0 | 4.0 GB | 8.8 GB | Too big | Get file → | |
| Q4_K_S | 4.1 GB | 8.8 GB | Too big | Get file → | |
| Q4_K_M | 4.3 GB | 9.1 GB | Too big | Get file → | |
| Q4_1 | 4.4 GB | 9.2 GB | Too big | Get file → | |
| Q5_K_S | 4.9 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_M | 5.0 GB | 9.8 GB | Too big | Get file → | |
| Q6_K | 5.8 GB | 10.6 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (1.67 GB, 6.5 GB memory) or IQ1_M (1.79 GB, 6.6 GB memory). If 12‑GB VRAM is available, Q4_K_M (4.27 GB, 9.1 GB memory) offers higher quality. For 16‑GB VRAM, Q5_K_M (4.99 GB, 9.8 GB memory) provides a good balance of size and performance. Estimates are approximate.
What GPU do you need for Omni R1 Zero?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 4.8 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_S (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.8 GB file, about 10.6 GB in use).
Which Omni R1 Zero quant should you choose?
Q4_K_M is the usual starting point for Omni R1 Zero: it balances file size and quality well. Here it is a 4.3 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 Omni R1 Zero
How much VRAM does Omni R1 Zero need?
About 9.1 GB at Q4_K_M with an 8K context window. That is the 4.3 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 Omni R1 Zero on an 8 GB GPU?
Yes, with IQ3_S: the 3.1 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 Omni R1 Zero GGUF?
It depends on the quant: file is 0.0 GB, IQ1_S is 1.7 GB, IQ1_M is 1.8 GB, IQ2_XXS is 2.0 GB, IQ2_XS is 2.2 GB, IQ2_S is 2.4 GB and 19 more.
What context length does Omni R1 Zero support?
The GGUF header lists a trained context length of 9,900 tokens (10K). The KV cache grows with the context you use: about 4.3 GB at 8K and 5.2 GB at 10K.
Where can I download Omni R1 Zero GGUF?
The files are on Hugging Face in the mradermacher/Omni-R1-Zero-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 Omni R1 Zero use?
Hugging Face lists the license as mit. 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 Omni R1 Zero on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations, which require about 6.5–6.6 GB of VRAM at 8k context.
Does Omni R1 Zero support vision tasks?
No, the model is trained without multimodal annotations and does not include vision support.