Falcon Mamba Tiny Dev needs about 0.5 GB of memory at Q4_K_M (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 22 quants, from 0.0 GB (IQ4_NL) to 0.0 GB (Q6_K).
Falcon Mamba Tiny Dev is a 9M-parameter Falcon model in GGUF format, quantized by RichardErkhov. Its trained context length is 1024K tokens. The repository has 22 quant files, from 0.0 GB (IQ4_NL) to 0.0 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_NL | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q8_0 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q2_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ3_XS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_L | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q3_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| IQ4_XS | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_1 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q4_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_1 | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_M | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q5_K_S | 0.0 GB | 0.5 GB | Fits | Get file → | |
| Q6_K | 0.0 GB | 0.5 GB | Fits | Get file → |
What GPU do you need for Falcon Mamba Tiny Dev?
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 (0.0 GB file, about 0.5 GB in use).
Which Falcon Mamba Tiny Dev quant should you choose?
Q4_K_M is the usual starting point for Falcon Mamba Tiny Dev: it balances file size and quality well. Here it is a 0.0 GB file.
The Q8_0 file is 0.0 GB, about 1.0 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 IQ4_NL at 0.0 GB, with the quality trade-offs that come with fewer bits. 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
Frequently asked questions about Falcon Mamba Tiny Dev
How much VRAM does Falcon Mamba Tiny Dev need?
About 0.5 GB at Q4_K_M with an 8K context window. That is the 0.0 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 Falcon Mamba Tiny Dev on an 8 GB GPU?
Yes, with Q6_K: the 0.0 GB file needs about 0.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Falcon Mamba Tiny Dev GGUF?
It depends on the quant: IQ4_NL is 0.0 GB, Q4_0 is 0.0 GB, Q5_0 is 0.0 GB, Q8_0 is 0.0 GB, Q2_K is 0.0 GB, IQ3_M is 0.0 GB and 16 more.
What context length does Falcon Mamba Tiny Dev support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K).
Where can I download Falcon Mamba Tiny Dev GGUF?
The files are on Hugging Face in the RichardErkhov/tiiuae_-_falcon-mamba-tiny-dev-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.