Cabra 72b i1 needs about 66.1 GB of memory at Q4_K_M (a 44.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 20 quants, from 16.2 GB (IQ1_S) to 49.9 GB (Q5_K_S). Longer context needs more: at 32K tokens the KV cache alone adds about 85.9 GB.
Cabra 72b i1 – a 72.3B Qwen2 model fine‑tuned for Portuguese
Cabra 72b i1 is a 72.3B parameter Qwen2 model fine‑tuned on the Cabra 30k dataset. It is optimized for Portuguese language generation. The model is released under a CC‑BY‑NC‑2.0 license and is intended for research use only.
Good at
- Portuguese language generation
- Fine‑tuned on Cabra 30k dataset
- Large context support up to 32768 tokens
Limits
- Not for commercial use
- No vision support
- Requires significant VRAM for larger quants
Best for
- Research on Portuguese LLMs
- Benchmarking Portuguese language tasks
- Exploring generative model behavior
Who it’s for. Researchers and developers working on Portuguese language models and generative AI. The model is available for non‑commercial use and requires a suitable GPU environment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 16.2 GB | 38.2 GB | Too big | Get file → | |
| IQ1_M | 17.6 GB | 39.5 GB | Too big | Get file → | |
| IQ2_XXS | 19.8 GB | 41.8 GB | Too big | Get file → | |
| IQ2_XS | 21.7 GB | 43.7 GB | Too big | Get file → | |
| IQ2_S | 23.4 GB | 45.3 GB | Too big | Get file → | |
| Q2_K_S | 24.8 GB | 46.8 GB | Too big | Get file → | |
| IQ2_M | 25.2 GB | 47.1 GB | Too big | Get file → | |
| IQ3_XXS | 27.7 GB | 49.7 GB | Too big | Get file → | |
| Q2_K | 28.5 GB | 50.4 GB | Too big | Get file → | |
| IQ3_XS | 29.9 GB | 51.9 GB | Too big | Get file → | |
| IQ3_S | 31.6 GB | 53.5 GB | Too big | Get file → | |
| Q3_K_S | 32.9 GB | 54.9 GB | Too big | Get file → | |
| IQ3_M | 33.9 GB | 55.9 GB | Too big | Get file → | |
| Q3_K_M | 35.9 GB | 57.9 GB | Too big | Get file → | |
| Q3_K_L | 38.5 GB | 60.5 GB | Too big | Get file → | |
| IQ4_XS | 38.8 GB | 60.8 GB | Too big | Get file → | |
| Q4_0 | 41.1 GB | 63.1 GB | Too big | Get file → | |
| Q4_K_S | 41.9 GB | 63.9 GB | Too big | Get file → | |
| Q4_K_M | 44.1 GB | 66.1 GB | Too big | Get file → | |
| Q5_K_S | 49.9 GB | 71.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (16.23 GB file, ~38.2 GB VRAM at 8 k context). For 12 GB VRAM, IQ1_M (17.57 GB file, ~39.5 GB VRAM). For 16 GB VRAM, IQ2_XXS (19.79 GB file, ~41.8 GB VRAM). Memory estimates are approximate.
What GPU do you need for Cabra 72b 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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: no quant fits at an 8K context.
- 48 GB VRAM: the best quant that fits is IQ2_M (25.2 GB file, about 47.1 GB in use).
Which Cabra 72b i1 quant should you choose?
Q4_K_M is the usual starting point for Cabra 72b i1: it balances file size and quality well. Here it is a 44.1 GB file.
If memory is tight, the smallest file is IQ1_S at 16.2 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 Cabra 72b i1
How much VRAM does Cabra 72b i1 need?
About 66.1 GB at Q4_K_M with an 8K context window. That is the 44.1 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 Cabra 72b i1 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 38.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Cabra 72b i1 GGUF?
It depends on the quant: IQ1_S is 16.2 GB, IQ1_M is 17.6 GB, IQ2_XXS is 19.8 GB, IQ2_XS is 21.7 GB, IQ2_S is 23.4 GB, Q2_K_S is 24.8 GB and 14 more.
What context length does Cabra 72b 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 21.5 GB at 8K and 85.9 GB at 32K.
Where can I download Cabra 72b i1 GGUF?
The files are on Hugging Face in the mradermacher/Cabra-72b-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 Cabra 72b i1 use?
Hugging Face lists the license as cc-by-nc-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 Cabra 72b i1 on 8 GB VRAM?
Use the IQ1_S quant, which requires about 38.2 GB VRAM at 8 k context. 8 GB VRAM is insufficient for any quant of this model.
Is this model suitable for commercial applications?
No. The CC‑BY‑NC‑2.0 license restricts commercial use. It is intended for research only.
What is the maximum context length supported?
The model supports up to 32768 tokens of context.