OpenCodeInterpreter-DS-6.7B needs about 7.4 GB of memory at IQ3_XXS (a 2.6 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 11 quants, from 1.5 GB (IQ1_S) to 13.5 GB.
OpenCodeInterpreter-DS-6.7B: 6.74B parameter code generation model
OpenCodeInterpreter-DS-6.7B is a 6.74B parameter model based on deepseek-coder-6.7b-base. It is optimized for code generation and execution tasks. The model supports a 16384 token context window and is released under the apache-2.0 license.
Good at
- Code generation
- Execution feedback integration
- Iterative refinement
Limits
- No vision support
- Requires recent llama.cpp build
- Large VRAM needed for higher quantizations
Best for
- Developers needing code generation
- Researchers testing execution feedback
- Integrating code generation into tools
Who it’s for. This model is suitable for developers and researchers who require a robust code generation system with execution and refinement capabilities. It is ideal for building or testing code interpreter pipelines.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ1_S | 1.5 GB | 6.3 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 → | |
| 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 → | |
| IQ3_M | 3.1 GB | 7.9 GB | Tight | Get file → | |
| IQ4_XS | 3.6 GB | 8.4 GB | Too big | Get file → | |
| — | 13.5 GB | 18.3 GB | Too big | Get file → |
For 8 GB VRAM, IQ2_XXS (1.86 GB, 6.7 GB memory at 8k context) is recommended. If 12 GB VRAM is available, IQ3_XXS (2.59 GB, 7.4 GB memory) offers better quality. For 16 GB VRAM, IQ4_XS (3.62 GB, 8.4 GB memory) provides higher fidelity.
What GPU do you need for OpenCodeInterpreter-DS-6.7B?
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 IQ4_XS (3.6 GB file, about 8.4 GB in use).
- 16 GB VRAM: the best quant that fits is IQ4_XS (3.6 GB file, about 8.4 GB in use).
- 24 GB VRAM: the best quant that fits is the main file (13.5 GB file, about 18.3 GB in use).
Which OpenCodeInterpreter-DS-6.7B quant should you choose?
IQ3_XXS (2.6 GB) is the middle option in this repository. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.
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 OpenCodeInterpreter-DS-6.7B
How much VRAM does OpenCodeInterpreter-DS-6.7B need?
About 7.4 GB at IQ3_XXS with an 8K context window. That is the 2.6 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 OpenCodeInterpreter-DS-6.7B 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 OpenCodeInterpreter-DS-6.7B GGUF?
It depends on the quant: IQ1_S is 1.5 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, IQ3_XXS is 2.6 GB and 5 more.
What context length does OpenCodeInterpreter-DS-6.7B 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 OpenCodeInterpreter-DS-6.7B GGUF?
The files are on Hugging Face in the CISCai/OpenCodeInterpreter-DS-6.7B-SOTA-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 OpenCodeInterpreter-DS-6.7B 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 OpenCodeInterpreter-DS-6.7B on 8 GB VRAM?
Yes, use the IQ2_XXS quantization which requires 1.86 GB file size and estimates 6.7 GB memory at 8k context.
Does this model support image inputs?
No, the model has no vision capabilities.
Which llama.cpp version is required?
Use llama.cpp from February 27th 2024 onwards for compatibility with the GGUFv3 files.