IQuestLab/IQuest-Coder-V1-40B-Instruct needs about 24.7 GB of memory at IQ4_XS (a 21.5 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 2 quants, from 21.5 GB (IQ4_XS) to 42.3 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.
IQuestLab/IQuest-Coder-V1-40B-Instruct is a 39.8B-parameter Iquest model in GGUF format, quantized by ilintar. Its trained context length is 128K tokens. The repository has 2 quant files, from 21.5 GB (IQ4_XS) to 42.3 GB (Q8_0).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ4_XS | 21.5 GB | 24.7 GB | Too big | Get file → | |
| Q8_0 | 42.3 GB | 45.5 GB | Too big | Get file → |
What GPU do you need for IQuestLab/IQuest-Coder-V1-40B-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: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: no quant fits at an 8K context.
- 32 GB VRAM: the best quant that fits is IQ4_XS (21.5 GB file, about 24.7 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (42.3 GB file, about 45.5 GB in use).
Which IQuestLab/IQuest-Coder-V1-40B-Instruct quant should you choose?
IQ4_XS (21.5 GB) is the middle option in this repository. The usual sweet spot between file size and quality, and the quant most people start with.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about IQuestLab/IQuest-Coder-V1-40B-Instruct
How much VRAM does IQuestLab/IQuest-Coder-V1-40B-Instruct need?
About 24.7 GB at IQ4_XS with an 8K context window. That is the 21.5 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 IQuestLab/IQuest-Coder-V1-40B-Instruct on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 24.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of IQuestLab/IQuest-Coder-V1-40B-Instruct GGUF?
It depends on the quant: IQ4_XS is 21.5 GB, Q8_0 is 42.3 GB.
What context length does IQuestLab/IQuest-Coder-V1-40B-Instruct support?
The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 2.7 GB at 8K and 10.7 GB at 32K.
Where can I download IQuestLab/IQuest-Coder-V1-40B-Instruct GGUF?
The files are on Hugging Face in the ilintar/IQuest-Coder-V1-40B-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 IQuestLab/IQuest-Coder-V1-40B-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.