CabraMistral7b v2 needs about 6.1 GB of memory at Q4_K_M (a 4.5 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 16 quants, from 2.9 GB (Q2_K) to 7.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
CabraMistral7b v2 – Portuguese‑optimized 7.24B LLM
CabraMistral7b v2 is a fine‑tuned version of Mistral 7b Instruct 0.2 on the Cabra 10k dataset. It is optimized for Portuguese and shows improved performance on Brazilian benchmarks. The model is released under a CC license for research use only.
Good at
- Portuguese language generation
- Research on generative models
- Benchmark performance in Brazil
Limits
- No commercial use
- No vision support
- Requires 8k context for estimates
Best for
- Academic research on LLMs
- Portuguese NLP experiments
- Benchmarking studies
Who it’s for. Researchers and developers working on Portuguese language models or studying generative AI. The model is provided for non‑commercial research purposes only.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.9 GB | 4.4 GB | Fits | Get file → | |
| IQ3_XS | 3.2 GB | 4.7 GB | Fits | Get file → | |
| Q3_K_S | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_S | 3.3 GB | 4.9 GB | Fits | Get file → | |
| IQ3_M | 3.4 GB | 5.0 GB | Fits | Get file → | |
| Q3_K_M | 3.7 GB | 5.2 GB | Fits | Get file → | |
| Q3_K_L | 4.0 GB | 5.6 GB | Fits | Get file → | |
| IQ4_XS | 4.1 GB | 5.7 GB | Fits | Get file → | |
| Q4_0 | 4.3 GB | 5.8 GB | Fits | Get file → | |
| Q4_K_S | 4.3 GB | 5.9 GB | Fits | Get file → | |
| IQ4_NL | 4.3 GB | 5.9 GB | Fits | Get file → | |
| Q4_K_M | 4.5 GB | 6.1 GB | Fits | Get file → | |
| Q5_K_S | 5.2 GB | 6.7 GB | Fits | Get file → | |
| Q5_K_M | 5.3 GB | 6.9 GB | Fits | Get file → | |
| Q6_K | 6.1 GB | 7.7 GB | Tight | Get file → | |
| Q8_0 | 7.8 GB | 9.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q4_K (est. 5.8 GB) or Q3_K_M (est. 5.2 GB). If you have 12 GB VRAM, Q5_K_S (est. 6.7 GB) or Q5_K_M (est. 6.9 GB) are suitable. For larger GPUs, Q6_K (est. 7.7 GB) or Q8_0 (est. 9.4 GB) provide higher fidelity.
What GPU do you need for CabraMistral7b v2?
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 IQ4_NL (4.3 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q6_K (6.1 GB file, about 7.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q8_0 (7.8 GB file, about 9.4 GB in use).
Which CabraMistral7b v2 quant should you choose?
Q4_K_M is the usual starting point for CabraMistral7b v2: it balances file size and quality well. Here it is a 4.5 GB file.
The Q8_0 file is 7.8 GB, about 1.7 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 2.9 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 CabraMistral7b v2
How much VRAM does CabraMistral7b v2 need?
About 6.1 GB at Q4_K_M with an 8K context window. That is the 4.5 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 CabraMistral7b v2 on an 8 GB GPU?
Yes, with Q6_K: the 6.1 GB file needs about 7.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of CabraMistral7b v2 GGUF?
It depends on the quant: Q2_K is 2.9 GB, IQ3_XS is 3.2 GB, Q3_K_S is 3.3 GB, IQ3_S is 3.3 GB, IQ3_M is 3.4 GB, Q3_K_M is 3.7 GB and 10 more.
What context length does CabraMistral7b v2 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 CabraMistral7b v2 GGUF?
The files are on Hugging Face in the mradermacher/CabraMistral7b-v2-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 CabraMistral7b v2 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 CabraMistral7b v2 on 8 GB VRAM?
Yes, use the Q4_K quantized file which requires approximately 5.8 GB of VRAM at 8k context.
Is this model suitable for commercial applications?
No. The model is licensed under CC for research use only and is prohibited for commercial use.
What context length does the model support?
The model was trained with a context length of 32768 tokens and supports up to that length.