ebft gemma4 26b lora lr5e6 merged needs about 19.3 GB of memory at Q4_K_M (a 16.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 4 quants, from 0.1 GB to 26.9 GB (Q8_0).
ebft gemma4 26b lora lr5e6 merged is a 25.2B-parameter Gemma model in GGUF format, quantized by AlexHung29629. Its trained context length is 256K tokens. The repository has 4 quant files, from 0.1 GB to 26.9 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 0.1 GB | 0.6 GB | Fits | Get file → | |
| Q4_0 | 14.5 GB | 16.7 GB | Too big | Get file → | |
| Q4_K_M | 16.8 GB | 19.3 GB | Too big | Get file → | |
| Q8_0 | 26.9 GB | 30.6 GB | Too big | Get file → |
What GPU do you need for ebft gemma4 26b lora lr5e6 merged?
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 the main file (0.1 GB file, about 0.6 GB in use).
- 6 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 8 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 12 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 16 GB VRAM: the best quant that fits is the main file (0.1 GB file, about 0.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q4_K_M (16.8 GB file, about 19.3 GB in use).
- 32 GB VRAM: the best quant that fits is Q8_0 (26.9 GB file, about 30.6 GB in use).
Which ebft gemma4 26b lora lr5e6 merged quant should you choose?
Q4_K_M is the usual starting point for ebft gemma4 26b lora lr5e6 merged: it balances file size and quality well. Here it is a 16.8 GB file.
The Q8_0 file is 26.9 GB, about 1.6 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 the first one in the table at 0.1 GB, with the quality trade-offs that come with fewer bits.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Frequently asked questions about ebft gemma4 26b lora lr5e6 merged
How much VRAM does ebft gemma4 26b lora lr5e6 merged need?
About 19.3 GB at Q4_K_M with an 8K context window. That is the 16.8 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 ebft gemma4 26b lora lr5e6 merged on an 8 GB GPU?
Yes, with the smaller files: the 0.1 GB file needs about 0.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ebft gemma4 26b lora lr5e6 merged GGUF?
It depends on the quant: file is 0.1 GB, Q4_0 is 14.5 GB, Q4_K_M is 16.8 GB, Q8_0 is 26.9 GB.
What context length does ebft gemma4 26b lora lr5e6 merged support?
The GGUF header lists a trained context length of 262,144 tokens (256K).
Where can I download ebft gemma4 26b lora lr5e6 merged GGUF?
The files are on Hugging Face in the AlexHung29629/ebft_gemma4_26b_lora_lr5e6_merged_GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.