deepseek-coder-6.7b-base 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. This repository has 21 quants, from 2.5 GB (Q2_K) to 5.5 GB (Q6_K).
DeepSeek Coder 6.7B base model for code generation
DeepSeek Coder 6.7B base is a code language model trained on 2T tokens with 87% code content. It supports project-level code completion and infilling with a 16K context window. The model is available in multiple GGUF quantizations.
Good at
- Code completion
- Project-level infilling
- Multi-language coding
Limits
- No vision support
- License terms not specified
- No mixture of experts
Best for
- Developers needing code generation
- Code completion tools
- Educational coding assistants
Who it’s for. Engineers and developers looking for a lightweight code model. The model is suitable for local deployment with GGUF support and llama.cpp inference.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 2.5 GB | 7.3 GB | Tight | Get file → | |
| IQ3_XS | 2.8 GB | 7.6 GB | Tight | Get file → | |
| IQ3_S | 3.0 GB | 7.7 GB | Tight | Get file → | |
| Q3_K_S | 3.0 GB | 7.7 GB | Tight | Get file → | |
| IQ3_M | 3.1 GB | 7.9 GB | Tight | Get file → | |
| Q3_K | 3.3 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_M | 3.3 GB | 8.1 GB | Too big | Get file → | |
| Q3_K_L | 3.6 GB | 8.4 GB | Too big | Get file → | |
| IQ4_XS | 3.6 GB | 8.4 GB | Too big | Get file → | |
| Q4_0 | 3.8 GB | 8.6 GB | Too big | Get file → | |
| IQ4_NL | 3.9 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_S | 3.9 GB | 8.7 GB | Too big | Get file → | |
| Q4_K | 4.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_K_M | 4.1 GB | 8.9 GB | Too big | Get file → | |
| Q4_1 | 4.2 GB | 9.0 GB | Too big | Get file → | |
| Q5_0 | 4.7 GB | 9.4 GB | Too big | Get file → | |
| Q5_K_S | 4.7 GB | 9.4 GB | Too big | Get file → | |
| Q5_K | 4.8 GB | 9.6 GB | Too big | Get file → | |
| Q5_K_M | 4.8 GB | 9.6 GB | Too big | Get file → | |
| Q5_1 | 5.1 GB | 9.9 GB | Too big | Get file → | |
| Q6_K | 5.5 GB | 10.3 GB | Too big | Get file → |
For 8GB VRAM, use Q4_K_M (est. 8.9GB) or Q3_K_M (est. 8.1GB). For 12GB VRAM, Q5_K_M (est. 9.6GB) or Q6_K (est. 10.3GB) are suitable. Smaller quants like Q2_K (est. 7.3GB) fit 6GB VRAM but with lower quality.
What GPU do you need for deepseek-coder-6.7b-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 IQ3_M (3.1 GB file, about 7.9 GB in use).
- 12 GB VRAM: the best quant that fits is Q6_K (5.5 GB file, about 10.3 GB in use).
Which deepseek-coder-6.7b-base quant should you choose?
Q4_K_M is the usual starting point for deepseek-coder-6.7b-base: it balances file size and quality well. Here it is a 4.1 GB file.
If memory is tight, the smallest file is Q2_K at 2.5 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
Frequently asked questions about deepseek-coder-6.7b-base
How much VRAM does deepseek-coder-6.7b-base 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-base on an 8 GB GPU?
Yes, with IQ3_M: the 3.1 GB file needs about 7.9 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of deepseek-coder-6.7b-base GGUF?
It depends on the quant: Q2_K is 2.5 GB, IQ3_XS is 2.8 GB, IQ3_S is 3.0 GB, Q3_K_S is 3.0 GB, IQ3_M is 3.1 GB, Q3_K is 3.3 GB and 15 more.
What context length does deepseek-coder-6.7b-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 4.3 GB at 8K and 8.6 GB at 16K.
Where can I download deepseek-coder-6.7b-base GGUF?
The files are on Hugging Face in the RichardErkhov/deepseek-ai_-_deepseek-coder-6.7b-base-gguf repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
Can I run DeepSeek Coder on 8GB VRAM?
Yes, using Q4_K_M or Q3_K_M quants will fit within 8GB VRAM with approximate memory usage of 8.9GB or 8.1GB.
What context length does the model support?
The model supports a 16384 token context length.
Does the model have vision capabilities?
No, the model is purely text-based and does not support vision.