Mamba 790m Hf needs about 1.0 GB of memory at Q4_K_M (a 0.5 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.3 GB (Q2_K) to 1.6 GB (F16).
Mamba 790m Hf – a 0.79B parameter GGUF model
Mamba 790m Hf is a 0.79B parameter model based on the Mamba architecture. It supports a context length of 1,048,576 tokens. The model is available in multiple quantizations for different memory budgets.
Good at
- Efficient inference with low‑memory quants
- Large context handling
- Fast token generation
Limits
- No vision support
- License not specified
- No mixture of experts
Best for
- Local LLM inference on limited GPU
- Research prototyping
- Embedded AI applications
Who it’s for. Developers and researchers who need a compact Mamba model for local inference. The model is suitable for environments with limited GPU memory and requires a 1,048,576 token context.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 0.3 GB | 0.9 GB | Fits | Get file → | |
| IQ3_M | 0.4 GB | 0.9 GB | Fits | Get file → | |
| IQ3_S | 0.4 GB | 0.9 GB | Fits | Get file → | |
| IQ3_XS | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_L | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_M | 0.4 GB | 0.9 GB | Fits | Get file → | |
| Q3_K_S | 0.4 GB | 0.9 GB | Fits | Get file → | |
| IQ4_XS | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_M | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q4_K_S | 0.5 GB | 1.0 GB | Fits | Get file → | |
| Q5_K_M | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q5_K_S | 0.6 GB | 1.1 GB | Fits | Get file → | |
| Q6_K | 0.7 GB | 1.2 GB | Fits | Get file → | |
| Q8_0 | 0.9 GB | 1.5 GB | Fits | Get file → | |
| F16 | 1.6 GB | 2.3 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M or Q4_K_S (file size 0.48 GB, estimated memory 1 GB). For 12 GB VRAM, Q5_K_M or Q5_K_S (0.57 GB, 1.1 GB). For 16 GB VRAM, Q6_K (0.67 GB, 1.2 GB) or Q8_0 (0.85 GB, 1.5 GB).
What GPU do you need for Mamba 790m Hf?
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 F16 (1.6 GB file, about 2.3 GB in use).
Which Mamba 790m Hf quant should you choose?
Q4_K_M is the usual starting point for Mamba 790m Hf: it balances file size and quality well. Here it is a 0.5 GB file.
The Q8_0 file is 0.9 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 0.3 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 790m Hf
How much VRAM does Mamba 790m Hf need?
About 1.0 GB at Q4_K_M with an 8K context window. That is the 0.5 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 790m Hf on an 8 GB GPU?
Yes, with F16: the 1.6 GB file needs about 2.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Mamba 790m Hf GGUF?
It depends on the quant: Q2_K is 0.3 GB, IQ3_M is 0.4 GB, IQ3_S is 0.4 GB, IQ3_XS is 0.4 GB, Q3_K_L is 0.4 GB, Q3_K_M is 0.4 GB and 9 more.
What context length does Mamba 790m Hf support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Mamba 790m Hf GGUF?
The files are on Hugging Face in the mradermacher/mamba-790m-hf-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run Mamba 790m Hf on 8 GB VRAM?
Yes, use Q4_K_M or Q4_K_S quantizations; they require about 1 GB of VRAM at 8 k context.
Does the model support vision tasks?
No, the model has no vision capabilities.
What is the maximum context length?
The model supports a context length of 1,048,576 tokens.