Breeze-13B-32k-Instruct-v1_0 needs about 10.1 GB of memory at Q4_K_M (a 7.7 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 21 quants, from 2.8 GB (IQ1_S) to 10.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 7.5 GB.
Breeze-13B-32k-Instruct-v1_0 – 12.7B parameter instruction model
Breeze-13B-32k-Instruct-v1_0 is a 12.7B parameter model trained on a 32k token context. It is a merge of multiple Breeze-7B-32k-Instruct-v1_0 models. The model is released under the apache-2.0 license.
Good at
- Large context handling
- Instruction following
- Text generation
Limits
- No vision support
- Requires 32k context for full capability
- License is apache-2.0
Best for
- Chatbots needing long context
- Document summarization
- Code generation
Who it’s for. Developers building applications that need instruction following with a large context window. The model is suitable for users who can run GGUF files locally with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 2.8 GB | 5.2 GB | Fits | Get file → | |
| IQ1_M | 3.1 GB | 5.5 GB | Fits | Get file → | |
| IQ2_XXS | 3.5 GB | 5.9 GB | Fits | Get file → | |
| IQ2_XS | 3.9 GB | 6.3 GB | Fits | Get file → | |
| IQ2_S | 4.1 GB | 6.5 GB | Fits | Get file → | |
| IQ2_M | 4.4 GB | 6.8 GB | Fits | Get file → | |
| Q2_K | 4.8 GB | 7.2 GB | Fits | Get file → | |
| IQ3_XXS | 5.0 GB | 7.4 GB | Tight | Get file → | |
| IQ3_XS | 5.3 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_S | 5.6 GB | 8.0 GB | Tight | Get file → | |
| IQ3_S | 5.6 GB | 8.0 GB | Tight | Get file → | |
| IQ3_M | 5.8 GB | 8.2 GB | Too big | Get file → | |
| Q3_K_M | 6.2 GB | 8.6 GB | Too big | Get file → | |
| Q3_K_L | 6.7 GB | 9.1 GB | Too big | Get file → | |
| IQ4_XS | 6.9 GB | 9.3 GB | Too big | Get file → | |
| Q4_0 | 7.3 GB | 9.6 GB | Too big | Get file → | |
| Q4_K_S | 7.3 GB | 9.7 GB | Too big | Get file → | |
| Q4_K_M | 7.7 GB | 10.1 GB | Too big | Get file → | |
| Q5_K_S | 8.8 GB | 11.2 GB | Too big | Get file → | |
| Q5_K_M | 9.0 GB | 11.4 GB | Too big | Get file → | |
| Q6_K | 10.4 GB | 12.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (2.85 GB) or IQ1_M (3.1 GB). For 12 GB VRAM, use Q4_K_M (7.68 GB) or Q5_K_S (8.79 GB). For 16 GB VRAM, use Q6_K (10.44 GB). Memory estimates are approximate.
What GPU do you need for Breeze-13B-32k-Instruct-v1_0?
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 IQ2_XXS (3.5 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is IQ3_S (5.6 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K_M (9.0 GB file, about 11.4 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (10.4 GB file, about 12.8 GB in use).
Which Breeze-13B-32k-Instruct-v1_0 quant should you choose?
Q4_K_M is the usual starting point for Breeze-13B-32k-Instruct-v1_0: it balances file size and quality well. Here it is a 7.7 GB file.
If memory is tight, the smallest file is IQ1_S at 2.8 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 Breeze-13B-32k-Instruct-v1_0
How much VRAM does Breeze-13B-32k-Instruct-v1_0 need?
About 10.1 GB at Q4_K_M with an 8K context window. That is the 7.7 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 Breeze-13B-32k-Instruct-v1_0 on an 8 GB GPU?
Yes, with IQ3_S: the 5.6 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Breeze-13B-32k-Instruct-v1_0 GGUF?
It depends on the quant: IQ1_S is 2.8 GB, IQ1_M is 3.1 GB, IQ2_XXS is 3.5 GB, IQ2_XS is 3.9 GB, IQ2_S is 4.1 GB, IQ2_M is 4.4 GB and 15 more.
What context length does Breeze-13B-32k-Instruct-v1_0 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.9 GB at 8K and 7.5 GB at 32K.
Where can I download Breeze-13B-32k-Instruct-v1_0 GGUF?
The files are on Hugging Face in the mradermacher/Breeze-13B-32k-Instruct-v1_0-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 Breeze-13B-32k-Instruct-v1_0 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 Breeze-13B-32k-Instruct-v1_0 on 8 GB VRAM?
Yes, using IQ1_S or IQ1_M quants. They require about 5.2–5.5 GB of VRAM at 8k context.
Does Breeze-13B-32k-Instruct-v1_0 support vision?
No, the model has no vision capabilities.
What license applies to Breeze-13B-32k-Instruct-v1_0?
The model is released under the apache-2.0 license.