deepseek-coder-6.7B-kexer 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 23 quants, from 1.5 GB (IQ1_S) to 27.0 GB (F32).
DeepSeek Coder 6.7B code model in GGUF format
DeepSeek Coder 6.7B is a code‑centric language model trained on 2T tokens. It supports project‑level code completion with a 16K context window. The model is released under Apache‑2.0 and is available in multiple GGUF quantizations.
Good at
- Code completion
- Project‑level infilling
- Multi‑language coding
Limits
- No vision support
- Requires 16K context window
- License is Apache‑2.0
Best for
- Developers needing code generation
- Automated code review tools
- Educational coding assistants
Who it’s for. Engineers and researchers who need a large, open‑source code model for generating or completing code. The model is suitable for both commercial and academic use under its Apache‑2.0 license.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.5 GB | 6.3 GB | Fits | Get file → | |
| IQ1_M | 1.7 GB | 6.4 GB | Fits | Get file → | |
| IQ2_XXS | 1.9 GB | 6.7 GB | Fits | Get file → | |
| IQ2_XS | 2.0 GB | 6.8 GB | Fits | Get file → | |
| IQ2_S | 2.2 GB | 7.0 GB | Fits | Get file → | |
| IQ2_M | 2.4 GB | 7.2 GB | Fits | Get file → | |
| Q2_K | 2.5 GB | 7.3 GB | Tight | Get file → | |
| IQ3_XXS | 2.6 GB | 7.4 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_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 → | |
| IQ4_NL | 3.8 GB | 8.6 GB | Too big | Get file → | |
| Q4_K_S | 3.9 GB | 8.7 GB | Too big | Get file → | |
| Q4_K_M | 4.1 GB | 8.9 GB | Too big | Get file → | |
| Q5_K_S | 4.7 GB | 9.4 GB | Too big | Get file → | |
| Q5_K_M | 4.8 GB | 9.6 GB | Too big | Get file → | |
| Q6_K | 5.5 GB | 10.3 GB | Too big | Get file → | |
| Q8_0 | 7.2 GB | 12.0 GB | Too big | Get file → | |
| F32 | 27.0 GB | 31.8 GB | Too big | Get file → |
For 8 GB VRAM, use IQ1_S (1.53 GB) or IQ1_M (1.65 GB). For 12 GB VRAM, IQ4_K_M (4.08 GB) or Q5_K_S (4.65 GB) provide a good balance of size and quality. For maximum quality on 24 GB VRAM, Q6_K (5.53 GB) or Q8_0 (7.16 GB) are recommended. Memory estimates are approximate.
What GPU do you need for deepseek-coder-6.7B-kexer?
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 Q8_0 (7.2 GB file, about 12.0 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
- 24 GB VRAM: the best quant that fits is Q8_0 (7.2 GB file, about 12.0 GB in use).
- 32 GB VRAM: the best quant that fits is F32 (27.0 GB file, about 31.8 GB in use).
Which deepseek-coder-6.7B-kexer quant should you choose?
Q4_K_M is the usual starting point for deepseek-coder-6.7B-kexer: it balances file size and quality well. Here it is a 4.1 GB file.
The Q8_0 file is 7.2 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 IQ1_S at 1.5 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
Source
Frequently asked questions about deepseek-coder-6.7B-kexer
How much VRAM does deepseek-coder-6.7B-kexer 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-kexer 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-kexer GGUF?
It depends on the quant: IQ1_S is 1.5 GB, IQ1_M is 1.7 GB, IQ2_XXS is 1.9 GB, IQ2_XS is 2.0 GB, IQ2_S is 2.2 GB, IQ2_M is 2.4 GB and 17 more.
What context length does deepseek-coder-6.7B-kexer 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-kexer GGUF?
The files are on Hugging Face in the bartowski/deepseek-coder-6.7B-kexer-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-kexer use?
Hugging Face lists the license as apache-2.0. 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, use IQ1_S or IQ1_M quantizations; they fit within 8 GB VRAM with enough headroom.
Does the model support Chinese programming languages?
The training data includes Chinese, but the model is primarily focused on code generation across languages.
Is there a chat template for this model?
No chat template is specified; the default llama.cpp template is used.