RACRO 7B CRO needs about 5.7 GB of memory at Q4_K_M (a 4.7 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 24 quants, from 1.9 GB (IQ1_S) to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
RACRO 7B CRO – a 7.62B parameter vision‑enabled reasoning model
RACRO 7B CRO is a multimodal model built on the qwen2vl architecture. It aligns visual perception with a text‑only reasoner, enabling faithful image captioning for downstream reasoning tasks. The model is released under the apache‑2.0 license.
Good at
- Reasoning with visual inputs
- Tool‑use integration
- Caption‑guided reinforcement learning
Limits
- No vision support in non‑vision quant files
- Requires 8‑k context for memory estimates
- Large VRAM needed for higher quants
Best for
- Multimodal math and science benchmarks
- Caption‑driven reasoning pipelines
- Plug‑and‑play upgrades to advanced reasoners
Who it’s for. Developers building multimodal reasoning systems who need a decoupled vision‑language architecture. Researchers requiring a 7.62B parameter model with open‑source licensing.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.9 GB | 2.9 GB | Fits | Get file → | |
| IQ1_M | 2.0 GB | 3.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.3 GB | 3.2 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 3.4 GB | Fits | Get file → | |
| IQ2_S | 2.6 GB | 3.6 GB | Fits | Get file → | |
| IQ2_M | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q2_K_S | 2.8 GB | 3.8 GB | Fits | Get file → | |
| Q2_K | 3.0 GB | 4.0 GB | Fits | Get file → | |
| IQ3_XXS | 3.1 GB | 4.1 GB | Fits | Get file → | |
| IQ3_XS | 3.3 GB | 4.3 GB | Fits | Get file → | |
| Q3_K_S | 3.5 GB | 4.5 GB | Fits | Get file → | |
| IQ3_S | 3.5 GB | 4.5 GB | Fits | Get file → | |
| IQ3_M | 3.6 GB | 4.5 GB | Fits | Get file → | |
| Q3_K_M | 3.8 GB | 4.8 GB | Fits | Get file → | |
| Q3_K_L | 4.1 GB | 5.1 GB | Fits | Get file → | |
| IQ4_XS | 4.2 GB | 5.2 GB | Fits | Get file → | |
| IQ4_NL | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_0 | 4.4 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_S | 4.5 GB | 5.4 GB | Fits | Get file → | |
| Q4_K_M | 4.7 GB | 5.7 GB | Fits | Get file → | |
| Q4_1 | 4.9 GB | 5.8 GB | Fits | Get file → | |
| Q5_K_S | 5.3 GB | 6.3 GB | Fits | Get file → | |
| Q5_K_M | 5.4 GB | 6.4 GB | Fits | Get file → | |
| Q6_K | 6.3 GB | 7.2 GB | Tight | Get file → |
For 8‑GB VRAM, use IQ1_S (file size 1.9 GB, memory 2.9 GB at 8k context) or IQ1_M (2.04 GB, 3 GB). If 12‑GB VRAM is available, IQ2_S (2.6 GB, 3.6 GB) or Q4_K_M (4.68 GB, 5.7 GB) provide a balance of size and performance. Higher quants like Q6_K require more than 16 GB VRAM.
What GPU do you need for RACRO 7B CRO?
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 Q2_K (3.0 GB file, about 4.0 GB in use).
- 6 GB VRAM: the best quant that fits is Q4_1 (4.9 GB file, about 5.8 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 7.2 GB in use).
Which RACRO 7B CRO quant should you choose?
Q4_K_M is the usual starting point for RACRO 7B CRO: it balances file size and quality well. Here it is a 4.7 GB file.
If memory is tight, the smallest file is IQ1_S at 1.9 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about RACRO 7B CRO
How much VRAM does RACRO 7B CRO need?
About 5.7 GB at Q4_K_M with an 8K context window. That is the 4.7 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 RACRO 7B CRO on an 8 GB GPU?
Yes, with Q6_K: the 6.3 GB file needs about 7.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of RACRO 7B CRO GGUF?
It depends on the quant: IQ1_S is 1.9 GB, IQ1_M is 2.0 GB, IQ2_XXS is 2.3 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.6 GB, IQ2_M is 2.8 GB and 18 more.
What context length does RACRO 7B CRO support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download RACRO 7B CRO GGUF?
The files are on Hugging Face in the mradermacher/RACRO-7B-CRO-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 RACRO 7B CRO 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 RACRO 7B CRO on 8 GB VRAM?
Yes, the IQ1_S and IQ1_M quantizations fit within 8 GB VRAM, using approximately 2.9–3 GB of memory at 8k context.
Does the model support vision tasks?
Yes, RACRO 7B CRO is a vision model; mmproj files are included in the static repository for image processing.
What license applies to this model?
The model is released under the apache‑2.0 license, allowing free use and modification.