KAIROS MM Qwen2.5 VL SFT needs about 16.2 GB of memory at BF16 (a 15.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 8.1 GB (Q8_0) to 15.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
KAIROS MM Qwen2.5 VL SFT is a 7.62B-parameter Qwen model in GGUF format, quantized by prithivMLmods. Its trained context length is 125K tokens. The repository has 3 quant files, from 8.1 GB (Q8_0) to 15.2 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 8.1 GB | 9.1 GB | Too big | Get file → | |
| BF16 | 15.2 GB | 16.2 GB | Too big | Get file → | |
| F16 | 15.2 GB | 16.2 GB | Too big | Get file → |
What GPU do you need for KAIROS MM Qwen2.5 VL SFT?
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: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (8.1 GB file, about 9.1 GB in use).
- 24 GB VRAM: the best quant that fits is BF16 (15.2 GB file, about 16.2 GB in use).
Which KAIROS MM Qwen2.5 VL SFT quant should you choose?
BF16 (15.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 8.1 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about KAIROS MM Qwen2.5 VL SFT
How much VRAM does KAIROS MM Qwen2.5 VL SFT need?
About 16.2 GB at BF16 with an 8K context window. That is the 15.2 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 KAIROS MM Qwen2.5 VL SFT on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.1 GB, so you would need a larger GPU or CPU offloading.
What is the file size of KAIROS MM Qwen2.5 VL SFT GGUF?
It depends on the quant: Q8_0 is 8.1 GB, BF16 is 15.2 GB, F16 is 15.2 GB.
What context length does KAIROS MM Qwen2.5 VL SFT support?
The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download KAIROS MM Qwen2.5 VL SFT GGUF?
The files are on Hugging Face in the prithivMLmods/KAIROS-MM-Qwen2.5-VL-SFT-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 KAIROS MM Qwen2.5 VL SFT 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.