Mamba 2.8b Instruct needs about 3.8 GB of memory at Q8_0 (a 3.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 3 quants, from 1.9 GB (Q5_0) to 5.6 GB (BF16).
Mamba 2.8b Instruct is a 2.77B-parameter Mamba model in GGUF format, quantized by ansh0x. Its trained context length is 1024K tokens. The repository has 3 quant files, from 1.9 GB (Q5_0) to 5.6 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_0 | 1.9 GB | 2.7 GB | Fits | Get file → | |
| Q8_0 | 3.0 GB | 3.8 GB | Fits | Get file → | |
| BF16 | 5.6 GB | 6.7 GB | Fits | Get file → |
What GPU do you need for Mamba 2.8b Instruct?
These figures add the file size, an fp16 KV cache at an 8K context window 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: the best quant that fits is Q8_0 (3.0 GB file, about 3.8 GB in use).
- 6 GB VRAM: the best quant that fits is Q8_0 (3.0 GB file, about 3.8 GB in use).
- 8 GB VRAM: the best quant that fits is BF16 (5.6 GB file, about 6.7 GB in use).
Which Mamba 2.8b Instruct quant should you choose?
Q8_0 (3.0 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
If memory is tight, the smallest file is Q5_0 at 1.9 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Mamba 2.8b Instruct
How much VRAM does Mamba 2.8b Instruct need?
About 3.8 GB at Q8_0 with an 8K context window. That is the 3.0 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 Mamba 2.8b Instruct on an 8 GB GPU?
Yes, with BF16: the 5.6 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mamba 2.8b Instruct GGUF?
It depends on the quant: Q5_0 is 1.9 GB, Q8_0 is 3.0 GB, BF16 is 5.6 GB.
What context length does Mamba 2.8b Instruct support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Mamba 2.8b Instruct GGUF?
The files are on Hugging Face in the ansh0x/mamba-2.8b-instruct-openhermes-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 Mamba 2.8b Instruct 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.