gaja needs about 9.7 GB of memory at Q5_K_M (a 4.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 3 quants, from 3.9 GB (Q4_K_S) to 5.6 GB (Q6_K).
gaja is a 6.87B-parameter Gaja model in GGUF format, quantized by damerajee. Its trained context length is 4K tokens. The repository has 3 quant files, from 3.9 GB (Q4_K_S) to 5.6 GB (Q6_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_S | 3.9 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 4.9 GB | 7.5 GB | Tight | Get file → | |
| Q6_K | 5.6 GB | 8.3 GB | Too big | Get file → |
What GPU do you need for gaja?
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 Q6_K (5.6 GB file, about 10.4 GB in use).
Which gaja quant should you choose?
Q5_K_M (4.9 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 Q4_K_S at 3.9 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about gaja
How much VRAM does gaja need?
About 9.7 GB at Q5_K_M with an 8K context window. That is the 4.9 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 gaja on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of gaja GGUF?
It depends on the quant: Q4_K_S is 3.9 GB, Q5_K_M is 4.9 GB, Q6_K is 5.6 GB.
What context length does gaja support?
The GGUF header lists a trained context length of 4,096 tokens (4K). The KV cache grows with the context you use: about 4.3 GB at 8K and 2.1 GB at 4K.
Where can I download gaja GGUF?
The files are on Hugging Face in the damerajee/gaja-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.