shuttle-2.5-mini needs about 10.4 GB of memory at Q5_K_S (a 8.5 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 9 quants, from 3.2 GB (IQ1_M) to 24.5 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 5.4 GB.
shuttle-2.5-mini is a 12.2B-parameter Shuttle model in GGUF format, quantized by shuttleai. Its trained context length is 1000K tokens. The repository has 9 quant files, from 3.2 GB (IQ1_M) to 24.5 GB (BF16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_M | 3.2 GB | 5.1 GB | Fits | Get file → | |
| IQ4_NL | 7.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_K_S | 7.1 GB | 9.0 GB | Too big | Get file → | |
| Q4_K | 7.5 GB | 9.3 GB | Too big | Get file → | |
| Q5_K_S | 8.5 GB | 10.4 GB | Too big | Get file → | |
| Q5_K | 8.7 GB | 10.6 GB | Too big | Get file → | |
| Q6_K | 10.1 GB | 11.9 GB | Too big | Get file → | |
| Q8_0 | 13.0 GB | 14.9 GB | Too big | Get file → | |
| BF16 | 24.5 GB | 26.3 GB | Too big | Get file → |
What GPU do you need for shuttle-2.5-mini?
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: the best quant that fits is IQ1_M (3.2 GB file, about 5.1 GB in use).
- 8 GB VRAM: the best quant that fits is IQ1_M (3.2 GB file, about 5.1 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (10.1 GB file, about 11.9 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (13.0 GB file, about 14.9 GB in use).
- 32 GB VRAM: the best quant that fits is BF16 (24.5 GB file, about 26.3 GB in use).
Which shuttle-2.5-mini quant should you choose?
Q5_K_S (8.5 GB) is the middle option in this repository. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
If memory is tight, the smallest file is IQ1_M at 3.2 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 shuttle-2.5-mini
How much VRAM does shuttle-2.5-mini need?
About 10.4 GB at Q5_K_S with an 8K context window. That is the 8.5 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 shuttle-2.5-mini on an 8 GB GPU?
Yes, with IQ1_M: the 3.2 GB file needs about 5.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of shuttle-2.5-mini GGUF?
It depends on the quant: IQ1_M is 3.2 GB, IQ4_NL is 7.1 GB, Q4_K_S is 7.1 GB, Q4_K is 7.5 GB, Q5_K_S is 8.5 GB, Q5_K is 8.7 GB and 3 more.
What context length does shuttle-2.5-mini support?
The GGUF header lists a trained context length of 1,024,000 tokens (1000K). 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 shuttle-2.5-mini GGUF?
The files are on Hugging Face in the shuttleai/shuttle-2.5-mini-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 shuttle-2.5-mini 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.