Dory-Beam-4B-Accurate needs about 6.6 GB of memory at Q5_K_M (a 3.7 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 4 quants, from 3.7 GB (Q5_K_M) to 4.2 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 9.7 GB.
Dory-Beam-4B-Accurate is a 3.98B-parameter Dory model in GGUF format, quantized by ProCreations. Its trained context length is 256K tokens. The repository has 4 quant files, from 3.7 GB (Q5_K_M) to 4.2 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q5_K_M | 3.7 GB | 6.6 GB | Fits | Get file → | |
| Q5_K_M | 3.7 GB | 6.6 GB | Fits | Get file → | |
| Q8_0 | 4.2 GB | 7.1 GB | Fits | Get file → | |
| Q8_0 | 4.2 GB | 7.1 GB | Fits | Get file → |
What GPU do you need for Dory-Beam-4B-Accurate?
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: the best quant that fits is Q8_0 (4.2 GB file, about 7.1 GB in use).
Which Dory-Beam-4B-Accurate quant should you choose?
Q5_K_M (3.7 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 Q5_K_M at 3.7 GB, with the quality trade-offs that come with fewer bits. Closer to the original model than 4-bit, for a moderate increase in size. A good pick when you have memory to spare.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Dory-Beam-4B-Accurate
How much VRAM does Dory-Beam-4B-Accurate need?
About 6.6 GB at Q5_K_M with an 8K context window. That is the 3.7 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 Dory-Beam-4B-Accurate on an 8 GB GPU?
Yes, with Q8_0: the 4.2 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Dory-Beam-4B-Accurate GGUF?
It depends on the quant: Q5_K_M is 3.7 GB, Q5_K_M is 3.7 GB, Q8_0 is 4.2 GB, Q8_0 is 4.2 GB.
What context length does Dory-Beam-4B-Accurate support?
The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 2.4 GB at 8K and 9.7 GB at 32K.
Where can I download Dory-Beam-4B-Accurate GGUF?
The files are on Hugging Face in the ProCreations/Dory-Beam-4B-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 Dory-Beam-4B-Accurate use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.