deepseek-coder-6.7b-instruct needs about 8.9 GB of memory at Q4_K_M (a 4.1 GB file) with an 8K context window, so it fits on a 12 GB GPU.
DeepSeek Coder 6.7B Instruct – code‑focused LLM
DeepSeek Coder 6.7B Instruct is a 6.7B parameter model fine‑tuned on 2B instruction tokens. It supports project‑level code completion with a 16K context window. The model is available in GGUF format for llama.cpp.
Good at
- Project‑level code completion
- Fill‑in‑the‑blank code tasks
- Multi‑language coding support
Limits
- Requires 8.9 GB VRAM at 8K context
- No vision capabilities
- License is other, not MIT
Best for
- Code autocompletion in IDEs
- Generating code snippets for documentation
- Infilling missing code blocks
Who it’s for. Developers needing a large, instruction‑tuned code model. The model is suitable for open‑source projects and commercial use under its license terms.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 4.1 GB | 8.9 GB | Too big | Get file → |
The Q4_K_M quantization yields a 4.08 GB file and requires about 8.9 GB VRAM at 8K context. For 8 GB VRAM, this is the recommended quant. If more VRAM is available, higher‑precision quants can be used, but they are not listed here.
What GPU do you need for deepseek-coder-6.7b-instruct?
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: the best quant that fits is Q4_K_M (4.1 GB file, about 8.9 GB in use).
Which deepseek-coder-6.7b-instruct quant should you choose?
Q4_K_M is the usual starting point for deepseek-coder-6.7b-instruct: it balances file size and quality well. Here it is a 4.1 GB file.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about deepseek-coder-6.7b-instruct
How much VRAM does deepseek-coder-6.7b-instruct need?
About 8.9 GB at Q4_K_M with an 8K context window. That is the 4.1 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-6.7b-instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.9 GB, so you would need a larger GPU or CPU offloading.
What is the file size of deepseek-coder-6.7b-instruct GGUF?
It depends on the quant: Q4_K_M is 4.1 GB.
What context length does deepseek-coder-6.7b-instruct support?
The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 4.3 GB at 8K and 8.6 GB at 16K.
Where can I download deepseek-coder-6.7b-instruct GGUF?
The files are on Hugging Face in the godolike/deepseek-coder-6.7b-instruct-Q4_K_M-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-6.7b-instruct 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 this model on 8 GB VRAM?
Yes, the Q4_K_M quant requires about 8.9 GB VRAM at 8K context, which fits within an 8 GB VRAM budget with some headroom.
Does this model support image input?
No, it only handles text input and does not support vision tasks.
What license applies to this model?
The model is released under an other license, not MIT, and commercial use is allowed under its terms.