ggml bakllava 1 needs about 6.7 GB of memory at Q5_K (a 5.1 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 3 quants, from 4.4 GB (Q4_K) to 14.5 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 4.3 GB.
ggml bakllava 1 is a 7.24B-parameter LLaVA model in GGUF format, quantized by mys. Its trained context length is 32K tokens. The repository has 3 quant files, from 4.4 GB (Q4_K) to 14.5 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K | 4.4 GB | 5.9 GB | Fits | Get file → | |
| Q5_K | 5.1 GB | 6.7 GB | Fits | Get file → | |
| F16 | 14.5 GB | 16.1 GB | Too big | Get file → |
What GPU do you need for ggml bakllava 1?
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 Q4_K (4.4 GB file, about 5.9 GB in use).
- 8 GB VRAM: the best quant that fits is Q5_K (5.1 GB file, about 6.7 GB in use).
- 12 GB VRAM: the best quant that fits is Q5_K (5.1 GB file, about 6.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K (5.1 GB file, about 6.7 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (14.5 GB file, about 16.1 GB in use).
Which ggml bakllava 1 quant should you choose?
Q5_K (5.1 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 at 4.4 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 ggml bakllava 1
How much VRAM does ggml bakllava 1 need?
About 6.7 GB at Q5_K with an 8K context window. That is the 5.1 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 ggml bakllava 1 on an 8 GB GPU?
Yes, with Q5_K: the 5.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of ggml bakllava 1 GGUF?
It depends on the quant: Q4_K is 4.4 GB, Q5_K is 5.1 GB, F16 is 14.5 GB.
What context length does ggml bakllava 1 support?
The GGUF header lists a trained context length of 32,768 tokens (32K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.3 GB at 32K.
Where can I download ggml bakllava 1 GGUF?
The files are on Hugging Face in the mys/ggml_bakllava-1 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.