CabraMixtral 8x7b i1 needs about 30.0 GB of memory at Q4_K_M (a 28.4 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 22 quants, from 9.8 GB (IQ1_S) to 38.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
CabraMixtral 8x7b i1 – a Portuguese‑optimized Mixtral 8x7b finetune
CabraMixtral 8x7b i1 is a fine‑tuned version of Mixtral 8x7b using the Cabra 30k dataset. It is optimized for Portuguese and shows improved performance on Brazilian benchmarks compared to the base model. The model is available in multiple GGUF quantizations.
Good at
- Portuguese language tasks
- Brazilian benchmark improvements
- Research on generative models
Limits
- No commercial use – research only
- No vision support
- Requires 32768 context tokens
Best for
- Academic research on LLMs
- Portuguese NLP experiments
- Benchmarking Brazilian datasets
Who it’s for. Researchers and developers working on Portuguese language models or studying generative AI. The model is licensed for research purposes only and cannot be used commercially.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 9.8 GB | 11.4 GB | Too big | Get file → | |
| IQ1_M | 10.8 GB | 12.4 GB | Too big | Get file → | |
| IQ2_XXS | 12.6 GB | 14.1 GB | Too big | Get file → | |
| IQ2_XS | 13.9 GB | 15.5 GB | Too big | Get file → | |
| IQ2_S | 14.1 GB | 15.7 GB | Too big | Get file → | |
| IQ2_M | 15.5 GB | 17.1 GB | Too big | Get file → | |
| Q2_K_S | 16.0 GB | 17.6 GB | Too big | Get file → | |
| Q2_K | 17.3 GB | 18.9 GB | Too big | Get file → | |
| IQ3_XXS | 18.2 GB | 19.8 GB | Too big | Get file → | |
| IQ3_XS | 19.4 GB | 20.9 GB | Too big | Get file → | |
| IQ3_S | 20.4 GB | 22.0 GB | Too big | Get file → | |
| Q3_K_S | 20.4 GB | 22.0 GB | Too big | Get file → | |
| IQ3_M | 21.4 GB | 23.0 GB | Too big | Get file → | |
| Q3_K_M | 22.5 GB | 24.1 GB | Too big | Get file → | |
| Q3_K_L | 24.2 GB | 25.7 GB | Too big | Get file → | |
| IQ4_XS | 25.1 GB | 26.7 GB | Too big | Get file → | |
| Q4_0 | 26.6 GB | 28.1 GB | Too big | Get file → | |
| Q4_K_S | 26.7 GB | 28.3 GB | Too big | Get file → | |
| Q4_K_M | 28.4 GB | 30.0 GB | Too big | Get file → | |
| Q5_K_S | 32.2 GB | 33.8 GB | Too big | Get file → | |
| Q5_K_M | 33.2 GB | 34.8 GB | Too big | Get file → | |
| Q6_K | 38.4 GB | 40.0 GB | Too big | Get file → |
For 8‑GB VRAM, use IQ1_S (9.82 GB) or IQ1_M (10.85 GB). If you have 12‑GB VRAM, IQ2_XXS (12.56 GB) or IQ2_XS (13.92 GB) are suitable. For larger GPUs, consider Q4_K_M (28.45 GB) or higher quants for better quality.
What GPU do you need for CabraMixtral 8x7b i1?
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: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is IQ1_S (9.8 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ2_S (14.1 GB file, about 15.7 GB in use).
- 24 GB VRAM: the best quant that fits is IQ3_M (21.4 GB file, about 23.0 GB in use).
- 32 GB VRAM: the best quant that fits is Q4_K_M (28.4 GB file, about 30.0 GB in use).
- 48 GB VRAM: the best quant that fits is Q6_K (38.4 GB file, about 40.0 GB in use).
Which CabraMixtral 8x7b i1 quant should you choose?
Q4_K_M is the usual starting point for CabraMixtral 8x7b i1: it balances file size and quality well. Here it is a 28.4 GB file.
If memory is tight, the smallest file is IQ1_S at 9.8 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 CabraMixtral 8x7b i1
How much VRAM does CabraMixtral 8x7b i1 need?
About 30.0 GB at Q4_K_M with an 8K context window. That is the 28.4 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 CabraMixtral 8x7b i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.
What is the file size of CabraMixtral 8x7b i1 GGUF?
It depends on the quant: IQ1_S is 9.8 GB, IQ1_M is 10.8 GB, IQ2_XXS is 12.6 GB, IQ2_XS is 13.9 GB, IQ2_S is 14.1 GB, IQ2_M is 15.5 GB and 16 more.
What context length does CabraMixtral 8x7b i1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download CabraMixtral 8x7b i1 GGUF?
The files are on Hugging Face in the mradermacher/CabraMixtral-8x7b-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 CabraMixtral 8x7b i1 use?
Hugging Face lists the license as cc. 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?
Use IQ1_S or IQ1_M quantizations, which are 9.82 GB and 10.85 GB respectively. They fit within 8 GB VRAM with some overhead.
Is this model suitable for commercial deployment?
No. The license restricts use to research only; commercial use is prohibited.
What context length does the model support?
The model was trained with 32768 context tokens and supports that length.