CabraQwen7b i1 needs about 9.6 GB of memory at Q4_K_M (a 4.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 24 quants, from 2.0 GB (IQ1_S) to 6.3 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 17.2 GB.
CabraQwen7b i1 is a 7.72B-parameter Cabraqwen model in GGUF format, quantized by mradermacher. Its trained context length is 32K tokens. The repository has 24 quant files, from 2.0 GB (IQ1_S) to 6.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.0 GB | 6.8 GB | Fits | Get file → | |
| IQ1_M | 2.2 GB | 7.0 GB | Fits | Get file → | |
| IQ2_XXS | 2.4 GB | 7.2 GB | Fits | Get file → | |
| IQ2_XS | 2.5 GB | 7.3 GB | Tight | Get file → | |
| IQ2_S | 2.8 GB | 7.5 GB | Tight | Get file → | |
| Q2_K_S | 2.9 GB | 7.7 GB | Tight | Get file → | |
| IQ2_M | 2.9 GB | 7.7 GB | Tight | Get file → | |
| Q2_K | 3.1 GB | 7.9 GB | Tight | Get file → | |
| IQ3_XXS | 3.1 GB | 7.9 GB | Tight | Get file → | |
| IQ3_XS | 3.4 GB | 8.2 GB | Too big | Get file → | |
| IQ3_S | 3.6 GB | 8.4 GB | Too big | Get file → | |
| Q3_K_S | 3.6 GB | 8.4 GB | Too big | Get file → | |
| IQ3_M | 3.7 GB | 8.5 GB | Too big | Get file → | |
| Q3_K_M | 3.9 GB | 8.7 GB | Too big | Get file → | |
| Q3_K_L | 4.2 GB | 9.0 GB | Too big | Get file → | |
| IQ4_XS | 4.3 GB | 9.1 GB | Too big | Get file → | |
| IQ4_NL | 4.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_0 | 4.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_S | 4.5 GB | 9.3 GB | Too big | Get file → | |
| Q4_K_M | 4.8 GB | 9.6 GB | Too big | Get file → | |
| Q4_1 | 5.0 GB | 9.7 GB | Too big | Get file → | |
| Q5_K_S | 5.4 GB | 10.2 GB | Too big | Get file → | |
| Q5_K_M | 5.5 GB | 10.3 GB | Too big | Get file → | |
| Q6_K | 6.3 GB | 11.1 GB | Too big | Get file → |
What GPU do you need for CabraQwen7b 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: the best quant that fits is IQ3_XXS (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (6.3 GB file, about 11.1 GB in use).
Which CabraQwen7b i1 quant should you choose?
Q4_K_M is the usual starting point for CabraQwen7b i1: it balances file size and quality well. Here it is a 4.8 GB file.
If memory is tight, the smallest file is IQ1_S at 2.0 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 CabraQwen7b i1
How much VRAM does CabraQwen7b i1 need?
About 9.6 GB at Q4_K_M with an 8K context window. That is the 4.8 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 CabraQwen7b i1 on an 8 GB GPU?
Yes, with IQ3_XXS: 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 CabraQwen7b i1 GGUF?
It depends on the quant: IQ1_S is 2.0 GB, IQ1_M is 2.2 GB, IQ2_XXS is 2.4 GB, IQ2_XS is 2.5 GB, IQ2_S is 2.8 GB, Q2_K_S is 2.9 GB and 18 more.
What context length does CabraQwen7b 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 4.3 GB at 8K and 17.2 GB at 32K.
Where can I download CabraQwen7b i1 GGUF?
The files are on Hugging Face in the mradermacher/CabraQwen7b-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 CabraQwen7b 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.