k 27b needs about 21.2 GB of memory at Q4_K_M (a 16.5 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 11 quants, from 10.5 GB (Q2_K) to 28.7 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 16.6 GB.
k 27b – a 27B Gemma3 model fine‑tuned for vision
k 27b is a 27B‑parameter Gemma3 model fine‑tuned from unsloth/gemma-3-27b-it. It supports vision tasks and is released under the apache‑2.0 license. The model was trained with Unsloth and Huggingface's TRL library.
Good at
- Vision inference
- Large context up to 131072 tokens
- Fine‑tuned performance
Limits
- No language support listed
- Requires substantial VRAM for higher quants
- No non‑vision capabilities
Best for
- Vision‑centric LLM applications
- Image‑to‑text generation
- Multimodal research
Who it’s for. Developers and researchers needing a vision‑capable 27B Gemma3 model. The model is suitable for those who can allocate the required GPU memory and are comfortable working with GGUF files.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 10.5 GB | 15.2 GB | Too big | Get file → | |
| Q3_K_S | 12.2 GB | 16.8 GB | Too big | Get file → | |
| Q3_K_M | 13.4 GB | 18.1 GB | Too big | Get file → | |
| Q3_K_L | 14.5 GB | 19.2 GB | Too big | Get file → | |
| IQ4_XS | 14.9 GB | 19.6 GB | Too big | Get file → | |
| Q4_K_S | 15.7 GB | 20.3 GB | Too big | Get file → | |
| Q4_K_M | 16.5 GB | 21.2 GB | Too big | Get file → | |
| Q5_K_S | 18.8 GB | 23.4 GB | Too big | Get file → | |
| Q5_K_M | 19.3 GB | 23.9 GB | Too big | Get file → | |
| Q6_K | 22.2 GB | 26.8 GB | Too big | Get file → | |
| Q8_0 | 28.7 GB | 33.4 GB | Too big | Get file → |
For 8 GB VRAM, use Q2_K (10.5 GB file, 15.2 GB memory at 8 k context). For 16 GB VRAM, Q3_K_S (12.17 GB file, 16.8 GB memory) or Q3_K_M (13.44 GB file, 18.1 GB memory). For 24 GB VRAM, Q4_K_S (15.67 GB file, 20.3 GB memory) or Q4_K_M (16.55 GB file, 21.2 GB memory).
What GPU do you need for k 27b?
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: no quant fits at an 8K context.
- 16 GB VRAM: the best quant that fits is Q2_K (10.5 GB file, about 15.2 GB in use).
- 24 GB VRAM: the best quant that fits is Q5_K_M (19.3 GB file, about 23.9 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (22.2 GB file, about 26.8 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (28.7 GB file, about 33.4 GB in use).
Which k 27b quant should you choose?
Q4_K_M is the usual starting point for k 27b: it balances file size and quality well. Here it is a 16.5 GB file.
The Q8_0 file is 28.7 GB, about 1.7 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 10.5 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 k 27b
How much VRAM does k 27b need?
About 21.2 GB at Q4_K_M with an 8K context window. That is the 16.5 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 k 27b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 15.2 GB, so you would need a larger GPU or CPU offloading.
What is the file size of k 27b GGUF?
It depends on the quant: Q2_K is 10.5 GB, Q3_K_S is 12.2 GB, Q3_K_M is 13.4 GB, Q3_K_L is 14.5 GB, IQ4_XS is 14.9 GB, Q4_K_S is 15.7 GB and 5 more.
What context length does k 27b support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 4.2 GB at 8K and 16.6 GB at 32K.
Where can I download k 27b GGUF?
The files are on Hugging Face in the mradermacher/k-27b-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 k 27b 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.
Can I run k 27b on 8 GB VRAM?
Yes, using the Q2_K quant which requires about 15.2 GB memory at 8 k context.
Does k 27b support text generation?
The model is fine‑tuned for vision; text generation is not a primary focus.