phi2_llama-3-silver needs about 7.3 GB of memory at its main file (a 5.7 GB file) with an 8K context window, so it fits on a 8 GB GPU.
phi2_llama-3-silver is a 8.03B-parameter Llama model in GGUF format, quantized by bakkensus. Its trained context length is 8K tokens. The repository has 1 quant file, from 5.7 GB to 5.7 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 5.7 GB | 7.3 GB | Tight | Get file → |
What GPU do you need for phi2_llama-3-silver?
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 the main file (5.7 GB file, about 7.3 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about phi2_llama-3-silver
How much VRAM does phi2_llama-3-silver need?
About 7.3 GB at its main file with an 8K context window. That is the 5.7 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 phi2_llama-3-silver on an 8 GB GPU?
Yes, with the smaller files: the 5.7 GB file needs about 7.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of phi2_llama-3-silver GGUF?
It depends on the quant: file is 5.7 GB.
What context length does phi2_llama-3-silver support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 1.1 GB at 8K and 1.1 GB at 8K.
Where can I download phi2_llama-3-silver GGUF?
The files are on Hugging Face in the bakkensus/llama-3-silver-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.