FrogMini 14B needs about 8.6 GB of memory at IQ3_S (a 6.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 5 quants, from 4.6 GB (IQ2_XXS) to 12.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
FrogMini 14B is a 14.8B-parameter Frogmini model in GGUF format, quantized by PollardWeights. Its trained context length is 40K tokens. The repository has 5 quant files, from 4.6 GB (IQ2_XXS) to 12.1 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_XXS | 4.6 GB | 6.4 GB | Fits | Get file → | |
| IQ2_S | 5.9 GB | 7.8 GB | Tight | Get file → | |
| IQ3_S | 6.8 GB | 8.6 GB | Too big | Get file → | |
| IQ4_XS | 8.4 GB | 10.3 GB | Too big | Get file → | |
| Q6_K | 12.1 GB | 14.0 GB | Too big | Get file → |
What GPU do you need for FrogMini 14B?
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: the best quant that fits is IQ2_S (5.9 GB file, about 7.8 GB in use).
- 12 GB VRAM: the best quant that fits is IQ4_XS (8.4 GB file, about 10.3 GB in use).
- 16 GB VRAM: the best quant that fits is Q6_K (12.1 GB file, about 14.0 GB in use).
Which FrogMini 14B quant should you choose?
IQ3_S (6.8 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
If memory is tight, the smallest file is IQ2_XXS at 4.6 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 FrogMini 14B
How much VRAM does FrogMini 14B need?
About 8.6 GB at IQ3_S with an 8K context window. That is the 6.8 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 FrogMini 14B on an 8 GB GPU?
Yes, with IQ2_S: the 5.9 GB file needs about 7.8 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of FrogMini 14B GGUF?
It depends on the quant: IQ2_XXS is 4.6 GB, IQ2_S is 5.9 GB, IQ3_S is 6.8 GB, IQ4_XS is 8.4 GB, Q6_K is 12.1 GB.
What context length does FrogMini 14B support?
The GGUF header lists a trained context length of 40,960 tokens (40K). The KV cache grows with the context you use: about 1.3 GB at 8K and 5.4 GB at 32K.
Where can I download FrogMini 14B GGUF?
The files are on Hugging Face in the PollardWeights/FrogMini-14B-Pollard repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does FrogMini 14B use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.