deepseek-ai_deepseek-coder-5.7bmqa-base needs about 4.1 GB of memory at Q4_K_M (a 3.4 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 12 quants, from 2.4 GB (Q2_K) to 6.1 GB (Q8_0).
DeepSeek Coder 5.7B: a 5.7B parameter code model with 16K context.
DeepSeek Coder 5.7Bmqa Base is a 5.7 billion parameter model trained on 2 trillion tokens. It supports a 16,384 token context window and is optimized for code completion and infilling tasks. The model is available in multiple GGUF quantisations for local inference.
Good at
- Code completion
- Project‑level code infilling
- Multi‑language programming support
Limits
- Requires 16K context window
- Large VRAM needed for higher quants
- License is MIT with model‑specific terms
Best for
- Developers needing local code generation
- Open‑source projects requiring code completion
- Educational coding tools
Who it’s for. This model is suitable for developers, researchers, and educators who need a local code generation engine. It works best on systems with GPU support and sufficient VRAM for the chosen quantisation.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.4 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_S | 2.5 GB | 3.1 GB | Fits | Get file → | |
| Q3_K_M | 2.8 GB | 3.4 GB | Fits | Get file → | |
| Q3_K_L | 3.0 GB | 3.7 GB | Fits | Get file → | |
| Q4_0 | 3.2 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_S | 3.3 GB | 3.9 GB | Fits | Get file → | |
| Q4_K_M | 3.4 GB | 4.1 GB | Fits | Get file → | |
| Q5_0 | 3.9 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_S | 3.9 GB | 4.6 GB | Fits | Get file → | |
| Q5_K_M | 4.0 GB | 4.7 GB | Fits | Get file → | |
| Q6_K | 4.7 GB | 5.3 GB | Fits | Get file → | |
| Q8_0 | 6.1 GB | 6.7 GB | Fits | Get file → |
For 8 GB VRAM, use Q4_K_M (est. 4.1 GB) or Q4_K_S (3.9 GB). With 12 GB VRAM, Q5_K_M (4.7 GB) or Q6_K (5.3 GB) are suitable. For 16 GB VRAM, Q8_0 (6.7 GB) provides the highest quality.
What GPU do you need for deepseek-ai_deepseek-coder-5.7bmqa-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: the best quant that fits is Q4_K_S (3.3 GB file, about 3.9 GB in use).
- 6 GB VRAM: the best quant that fits is Q6_K (4.7 GB file, about 5.3 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (6.1 GB file, about 6.7 GB in use).
Which deepseek-ai_deepseek-coder-5.7bmqa-base quant should you choose?
Q4_K_M is the usual starting point for deepseek-ai_deepseek-coder-5.7bmqa-base: it balances file size and quality well. Here it is a 3.4 GB file.
The Q8_0 file is 6.1 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 2.4 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-ai_deepseek-coder-5.7bmqa-base
How much VRAM does deepseek-ai_deepseek-coder-5.7bmqa-base need?
About 4.1 GB at Q4_K_M with an 8K context window. That is the 3.4 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-ai_deepseek-coder-5.7bmqa-base on an 8 GB GPU?
Yes, with Q8_0: the 6.1 GB file needs about 6.7 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of deepseek-ai_deepseek-coder-5.7bmqa-base GGUF?
It depends on the quant: Q2_K is 2.4 GB, Q3_K_S is 2.5 GB, Q3_K_M is 2.8 GB, Q3_K_L is 3.0 GB, Q4_0 is 3.2 GB, Q4_K_S is 3.3 GB and 6 more.
What context length does deepseek-ai_deepseek-coder-5.7bmqa-base support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 0.1 GB at 8K and 0.3 GB at 16K.
Where can I download deepseek-ai_deepseek-coder-5.7bmqa-base GGUF?
The files are on Hugging Face in the TheBloke/deepseek-coder-5.7bmqa-base-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-ai_deepseek-coder-5.7bmqa-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 5.7B on 8 GB VRAM?
Yes, using Q4_K_M or Q4_K_S quantisations, which require about 4 GB of VRAM at 8K context.
Does this model support vision tasks?
No, the model is trained only for code and does not include vision capabilities.
Is commercial use allowed?
Yes, the model is licensed under MIT and supports commercial use per the model license.