EAGLE vicuna 7b v1.3 f16 needs about 1.6 GB of memory at F16 (a 1.0 GB file) with an 8K context window, so it fits on a 4 GB GPU.
EAGLE vicuna 7b v1.3 f16 is a 498M-parameter Eagle model in GGUF format, quantized by shuaiye. Its trained context length is 2K tokens. The repository has 1 quant file, from 1.0 GB (F16) to 1.0 GB (F16).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| F16 | 1.0 GB | 1.5 GB | Fits | Get file → |
What GPU do you need for EAGLE vicuna 7b v1.3 f16?
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: the best quant that fits is F16 (1.0 GB file, about 1.6 GB in use).
Which EAGLE vicuna 7b v1.3 f16 quant should you choose?
F16 (1.0 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about EAGLE vicuna 7b v1.3 f16
How much VRAM does EAGLE vicuna 7b v1.3 f16 need?
About 1.6 GB at F16 with an 8K context window. That is the 1.0 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 EAGLE vicuna 7b v1.3 f16 on an 8 GB GPU?
Yes, with F16: the 1.0 GB file needs about 1.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of EAGLE vicuna 7b v1.3 f16 GGUF?
It depends on the quant: F16 is 1.0 GB.
What context length does EAGLE vicuna 7b v1.3 f16 support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.0 GB at 2K.
Where can I download EAGLE vicuna 7b v1.3 f16 GGUF?
The files are on Hugging Face in the shuaiye/EAGLE-vicuna-7b-v1.3-f16 repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.