Zamba2 2.7B Instruct v2 needs about 11.8 GB of memory at Q4_0 (a 2.2 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 2 quants, from 2.2 GB (Q4_0) to 4.2 GB (Q8_0).
Zamba2 2.7B Instruct v2 is a 3.91B-parameter Zamba model in GGUF format, quantized by EchoLabs33. Its trained context length is 4K tokens. The repository has 2 quant files, from 2.2 GB (Q4_0) to 4.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_0 | 2.2 GB | 7.3 GB | Tight | Get file → | |
| Q8_0 | 4.2 GB | 9.2 GB | Too big | Get file → |
What GPU do you need for Zamba2 2.7B Instruct 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: 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 Q4_0 (2.2 GB file, about 11.8 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (4.2 GB file, about 13.7 GB in use).
Which Zamba2 2.7B Instruct v2 quant should you choose?
Q4_0 (2.2 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Zamba2 2.7B Instruct v2
How much VRAM does Zamba2 2.7B Instruct v2 need?
About 11.8 GB at Q4_0 with an 8K context window. That is the 2.2 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 Zamba2 2.7B Instruct v2 on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 11.8 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Zamba2 2.7B Instruct v2 GGUF?
It depends on the quant: Q4_0 is 2.2 GB, Q8_0 is 4.2 GB.
What context length does Zamba2 2.7B Instruct v2 support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 9.1 GB at 8K and 4.5 GB at 4K.
Where can I download Zamba2 2.7B Instruct v2 GGUF?
The files are on Hugging Face in the EchoLabs33/Zamba2-2.7B-Instruct-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 Zamba2 2.7B Instruct v2 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.