DeciLM 7B instruct needs about 15.3 GB of memory at F16 (a 14.2 GB file) with an 8K context window, so it fits on a 16 GB GPU. This repository has 3 quants, from 7.6 GB (Q8_0) to 28.4 GB (F32).
DeciLM 7B instruct – a 7.11B llama-based instruction model
DeciLM 7B instruct is a 7.11B parameter model built on the llama architecture. It is available in GGUF format and supports a 8192 token context window. The model is released under the apache-2.0 license.
Good at
- Instruction following
- Text generation
- Conversational tasks
Limits
- No vision support
- Requires 8.6 GB VRAM for Q8_0 at 8k context
- License is apache-2.0
Best for
- Chatbots
- Content drafting
- Code assistance
Who it’s for. Developers and researchers needing a lightweight instruction model for CPU or GPU inference. The model is suitable for local deployment with llama.cpp.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q8_0 | 7.6 GB | 8.6 GB | Too big | Get file → | |
| F16 | 14.2 GB | 15.3 GB | Too big | Get file → | |
| F32 | 28.4 GB | 29.5 GB | Too big | Get file → |
For 8 GB VRAM, use Q8_0 (7.55 GB file, 8.6 GB memory). If more VRAM is available, F16 (14.22 GB file, 15.3 GB memory) offers higher precision. F32 (28.43 GB file, 29.5 GB memory) is only for systems with large memory budgets.
What GPU do you need for DeciLM 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 Q8_0 (7.6 GB file, about 8.6 GB in use).
- 16 GB VRAM: the best quant that fits is F16 (14.2 GB file, about 15.3 GB in use).
- 24 GB VRAM: the best quant that fits is F16 (14.2 GB file, about 15.3 GB in use).
- 32 GB VRAM: the best quant that fits is F32 (28.4 GB file, about 29.5 GB in use).
Which DeciLM 7B instruct quant should you choose?
F16 (14.2 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.
If memory is tight, the smallest file is Q8_0 at 7.6 GB, with the quality trade-offs that come with fewer bits. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about DeciLM 7B instruct
How much VRAM does DeciLM 7B instruct need?
About 15.3 GB at F16 with an 8K context window. That is the 14.2 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 DeciLM 7B instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 8.6 GB, so you would need a larger GPU or CPU offloading.
What is the file size of DeciLM 7B instruct GGUF?
It depends on the quant: Q8_0 is 7.6 GB, F16 is 14.2 GB, F32 is 28.4 GB.
What context length does DeciLM 7B instruct support?
The GGUF header lists a trained context length of 8,192 tokens (8K). The KV cache grows with the context you use: about 0.5 GB at 8K and 0.5 GB at 8K.
Where can I download DeciLM 7B instruct GGUF?
The files are on Hugging Face in the Deci/DeciLM-7B-instruct-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 DeciLM 7B instruct 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 DeciLM 7B instruct on 8 GB VRAM?
Yes, the Q8_0 quantization requires about 8.6 GB VRAM at 8k context, which fits on an 8 GB GPU with some headroom.
Does DeciLM 7B support vision tasks?
No, the model does not have vision capabilities.
What license does DeciLM 7B use?
The model is released under the apache-2.0 license.