Mamba 3B needs about 2.3 GB of memory at Q4_K_M (a 1.6 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.7 GB (IQ1_S) to 2.3 GB (Q6_K).
Mamba 3B is a 2.77B-parameter Mamba model in GGUF format, quantized by mradermacher. Its trained context length is 1024K tokens. The repository has 22 quant files, from 0.7 GB (IQ1_S) to 2.3 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 0.7 GB | 1.2 GB | Fits | Get file → | |
| IQ1_M | 0.7 GB | 1.3 GB | Fits | Get file → | |
| IQ2_XXS | 0.8 GB | 1.4 GB | Fits | Get file → | |
| IQ2_S | 0.9 GB | 1.5 GB | Fits | Get file → | |
| IQ2_XS | 0.9 GB | 1.5 GB | Fits | Get file → | |
| IQ2_M | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q2_K | 1.0 GB | 1.6 GB | Fits | Get file → | |
| Q2_K_S | 1.0 GB | 1.6 GB | Fits | Get file → | |
| IQ3_XXS | 1.1 GB | 1.8 GB | Fits | Get file → | |
| IQ3_M | 1.3 GB | 1.9 GB | Fits | Get file → | |
| IQ3_S | 1.3 GB | 1.9 GB | Fits | Get file → | |
| IQ3_XS | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_L | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_M | 1.3 GB | 1.9 GB | Fits | Get file → | |
| Q3_K_S | 1.3 GB | 1.9 GB | Fits | Get file → | |
| IQ4_XS | 1.5 GB | 2.2 GB | Fits | Get file → | |
| Q4_0 | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_M | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q4_K_S | 1.6 GB | 2.3 GB | Fits | Get file → | |
| Q5_K_M | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q5_K_S | 2.0 GB | 2.7 GB | Fits | Get file → | |
| Q6_K | 2.3 GB | 3.1 GB | Fits | Get file → |
What GPU do you need for Mamba 3B?
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 Q6_K (2.3 GB file, about 3.1 GB in use).
Which Mamba 3B quant should you choose?
Q4_K_M is the usual starting point for Mamba 3B: it balances file size and quality well. Here it is a 1.6 GB file.
If memory is tight, the smallest file is IQ1_S at 0.7 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 Mamba 3B
How much VRAM does Mamba 3B need?
About 2.3 GB at Q4_K_M with an 8K context window. That is the 1.6 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 3B on an 8 GB GPU?
Yes, with Q6_K: the 2.3 GB file needs about 3.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mamba 3B GGUF?
It depends on the quant: IQ1_S is 0.7 GB, IQ1_M is 0.7 GB, IQ2_XXS is 0.8 GB, IQ2_S is 0.9 GB, IQ2_XS is 0.9 GB, IQ2_M is 1.0 GB and 16 more.
What context length does Mamba 3B support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Mamba 3B GGUF?
The files are on Hugging Face in the mradermacher/Mamba-3B-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 Mamba 3B 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.