Omni R1 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 – 7B parameter model focused on reasoning
Omni R1 is a 7B parameter model trained with multimodal interleaved supervision. It supports reasoning tasks within a 5120 token context window. The model is available in multiple GGUF quantizations.
Good at
- Reasoning
- Multimodal interleaved tasks
- Stable functional image generation
Limits
- 5120 token context limit
- No vision support beyond training
- License not specified
Best for
- Chatbot reasoning
- Text generation with context
- Research prototyping
Who it’s for. Developers and researchers needing a reasoning‑oriented LLM with a moderate context window. The model is suitable for local deployment via llama.cpp or vLLM.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.0 GB | 3.2 GB | Fits | Get file → | |
| IQ1_S | 1.7 GB | 4.9 GB | Fits | Get file → | |
| IQ1_M | 1.8 GB | 5.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.0 GB | 5.2 GB | Fits | Get file → | |
| IQ2_XS | 2.2 GB | 5.4 GB | Fits | Get file → | |
| IQ2_S | 2.4 GB | 5.5 GB | Fits | Get file → | |
| Q2_K_S | 2.5 GB | 5.7 GB | Fits | Get file → | |
| IQ2_M | 2.5 GB | 5.7 GB | Fits | Get file → | |
| Q2_K | 2.7 GB | 5.9 GB | Fits | Get file → | |
| IQ3_XXS | 2.7 GB | 5.9 GB | Fits | Get file → | |
| IQ3_XS | 3.0 GB | 6.2 GB | Fits | Get file → | |
| IQ3_S | 3.1 GB | 6.3 GB | Fits | Get file → | |
| Q3_K_S | 3.1 GB | 6.3 GB | Fits | Get file → | |
| IQ3_M | 3.3 GB | 6.5 GB | Fits | Get file → | |
| Q3_K_M | 3.5 GB | 6.7 GB | Fits | Get file → | |
| Q3_K_L | 3.8 GB | 7.0 GB | Fits | Get file → | |
| IQ4_XS | 3.8 GB | 7.0 GB | Fits | Get file → | |
| IQ4_NL | 4.0 GB | 7.2 GB | Tight | Get file → | |
| Q4_0 | 4.0 GB | 7.2 GB | Tight | Get file → | |
| Q4_K_S | 4.1 GB | 7.2 GB | Tight | Get file → | |
| Q4_K_M | 4.3 GB | 7.5 GB | Tight | Get file → | |
| Q4_1 | 4.4 GB | 7.6 GB | Tight | Get file → | |
| Q5_K_S | 4.9 GB | 8.0 GB | Too big | Get file → | |
| Q5_K_M | 5.0 GB | 8.2 GB | Too big | Get file → | |
| Q6_K | 5.8 GB | 8.9 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (6.5 GB) or IQ1_M (6.6 GB). If 12 GB VRAM is available, IQ2_S (7.1 GB) or Q2_K (7.5 GB) are good choices. Higher quality quants such as Q3_K_M (8.3 GB) require 16 GB or more.
What GPU do you need for Omni R1?
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 quant should you choose?
Q4_K_M is the usual starting point for Omni R1: 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
How much VRAM does Omni R1 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 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 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 support?
The GGUF header lists a trained context length of 5,120 tokens (5K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.7 GB at 5K.
Where can I download Omni R1 GGUF?
The files are on Hugging Face in the mradermacher/Omni-R1-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Omni R1 on 8 GB VRAM?
Yes, use IQ1_S or IQ1_M quantizations, which estimate 6.5–6.6 GB memory at 8 k context.
What is the maximum context length?
The model supports up to 5120 tokens in context.
Does Omni R1 support vision tasks?
No, the model is trained for reasoning and does not include vision inference.