DeepSeek V2 Lite Chat ReMoE needs about 17.7 GB of memory at its main file (a 16.7 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 2 quants, from 16.7 GB to 31.4 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 1.9 GB.
DeepSeek V2 Lite Chat ReMoE is a 15.7B-parameter DeepSeek model in GGUF format, quantized by Zhu149248. Its trained context length is 160K tokens. The repository has 2 quant files, from 16.7 GB to 31.4 GB.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| — | 16.7 GB | 17.7 GB | Too big | Get file → | |
| — | 31.4 GB | 32.4 GB | Too big | Get file → |
What GPU do you need for DeepSeek V2 Lite Chat ReMoE?
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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is the main file (16.7 GB file, about 17.7 GB in use).
- 32 GB VRAM: the best quant that fits is the main file (16.7 GB file, about 17.7 GB in use).
- 48 GB VRAM: the best quant that fits is the main file (31.4 GB file, about 32.4 GB in use).
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek V2 Lite Chat ReMoE
How much VRAM does DeepSeek V2 Lite Chat ReMoE need?
About 17.7 GB at its main file with an 8K context window. That is the 16.7 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 DeepSeek V2 Lite Chat ReMoE on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 17.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeepSeek V2 Lite Chat ReMoE GGUF?
It depends on the quant: file is 16.7 GB, file is 31.4 GB.
What context length does DeepSeek V2 Lite Chat ReMoE support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 0.5 GB at 8K and 1.9 GB at 32K.
Where can I download DeepSeek V2 Lite Chat ReMoE GGUF?
The files are on Hugging Face in the Zhu149248/DeepSeek-V2-Lite-Chat-ReMoE-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 DeepSeek V2 Lite Chat ReMoE 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.