DeepSeek-Coder-V2-Lite-Base needs about 13.1 GB of memory at Q4_K_M (a 10.4 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 21 quants, from 5.0 GB (IQ1_S) to 14.1 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 9.1 GB.
DeepSeek-Coder-V2-Lite-Base: 15.7B parameter code model with 128K context
DeepSeek-Coder-V2-Lite-Base is a 15.7B parameter mixture-of-experts model designed for code generation and completion. It supports 128K context tokens and is available in multiple GGUF quantizations. The model is open‑source and can be run locally with llama.cpp or vLLM.
Good at
- Code completion
- Code insertion
- Chat completion
Limits
- Requires 128K context support
- No vision capabilities
- License is other
Best for
- Developers needing local code generation
- Educational coding tools
- Rapid prototyping of coding assistants
Who it’s for. Engineers and researchers who want a large code‑focused model that can be run locally. The model is suitable for developers who need a high‑capacity code assistant without relying on external APIs.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 5.0 GB | 7.8 GB | Tight | Get file → | |
| IQ1_M | 5.2 GB | 8.0 GB | Too big | Get file → | |
| IQ2_XXS | 5.6 GB | 8.4 GB | Too big | Get file → | |
| IQ2_XS | 6.0 GB | 8.7 GB | Too big | Get file → | |
| IQ2_S | 6.0 GB | 8.8 GB | Too big | Get file → | |
| IQ2_M | 6.3 GB | 9.1 GB | Too big | Get file → | |
| Q2_K | 6.4 GB | 9.2 GB | Too big | Get file → | |
| IQ3_XXS | 7.0 GB | 9.7 GB | Too big | Get file → | |
| IQ3_XS | 7.1 GB | 9.9 GB | Too big | Get file → | |
| IQ3_S | 7.5 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_S | 7.5 GB | 10.3 GB | Too big | Get file → | |
| IQ3_M | 7.6 GB | 10.3 GB | Too big | Get file → | |
| Q3_K_M | 8.1 GB | 10.9 GB | Too big | Get file → | |
| Q3_K_L | 8.5 GB | 11.2 GB | Too big | Get file → | |
| IQ4_XS | 8.6 GB | 11.3 GB | Too big | Get file → | |
| Q4_0 | 8.9 GB | 11.7 GB | Too big | Get file → | |
| Q4_K_S | 9.5 GB | 12.3 GB | Too big | Get file → | |
| Q4_K_M | 10.4 GB | 13.1 GB | Too big | Get file → | |
| Q5_K_S | 11.1 GB | 13.9 GB | Too big | Get file → | |
| Q5_K_M | 11.9 GB | 14.6 GB | Too big | Get file → | |
| Q6_K | 14.1 GB | 16.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (file size 4.99 GB, estimated 7.8 GB memory). For 12 GB VRAM, IQ4_K_S (9.53 GB, 12.3 GB memory). For 16 GB VRAM, Q5_K_M (11.85 GB, 14.6 GB memory). Estimates are approximate.
What GPU do you need for DeepSeek-Coder-V2-Lite-Base?
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 IQ1_M (5.2 GB file, about 8.0 GB in use).
- 12 GB VRAM: the best quant that fits is Q4_0 (8.9 GB file, about 11.7 GB in use).
- 16 GB VRAM: the best quant that fits is Q5_K_M (11.9 GB file, about 14.6 GB in use).
- 24 GB VRAM: the best quant that fits is Q6_K (14.1 GB file, about 16.8 GB in use).
Which DeepSeek-Coder-V2-Lite-Base quant should you choose?
Q4_K_M is the usual starting point for DeepSeek-Coder-V2-Lite-Base: it balances file size and quality well. Here it is a 10.4 GB file.
If memory is tight, the smallest file is IQ1_S at 5.0 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeepSeek-Coder-V2-Lite-Base
How much VRAM does DeepSeek-Coder-V2-Lite-Base need?
About 13.1 GB at Q4_K_M with an 8K context window. That is the 10.4 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-Coder-V2-Lite-Base on an 8 GB GPU?
Yes, with IQ1_M: the 5.2 GB file needs about 8.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of DeepSeek-Coder-V2-Lite-Base GGUF?
It depends on the quant: IQ1_S is 5.0 GB, IQ1_M is 5.2 GB, IQ2_XXS is 5.6 GB, IQ2_XS is 6.0 GB, IQ2_S is 6.0 GB, IQ2_M is 6.3 GB and 15 more.
What context length does DeepSeek-Coder-V2-Lite-Base support?
The GGUF header lists a trained context length of 163,840 tokens (160K). The KV cache grows with the context you use: about 2.3 GB at 8K and 9.1 GB at 32K.
Where can I download DeepSeek-Coder-V2-Lite-Base GGUF?
The files are on Hugging Face in the mradermacher/DeepSeek-Coder-V2-Lite-Base-i1-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-Coder-V2-Lite-Base 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.
Can I run DeepSeek-Coder-V2-Lite-Base on 8 GB VRAM?
Yes, using the IQ1_S quantization which requires about 7.8 GB of VRAM at 8K context.
Does the model support vision tasks?
No, the model is purely text and code focused.
What context length does the model support?
The model supports up to 128K tokens of context.