IQ

IQuest Coder V1 40B Instruct

IquestGGUF by mradermacherUpdated 2026-01-02
Download on Hugging Face
Parameters39.8B
Context128K
Layers80
Architecturellama
Smallest quant0.0 GB
Quick answer

IQuest Coder V1 40B Instruct needs about 27.2 GB of memory at Q4_K_M (a 24.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 24 quants, from 0.0 GB to 32.6 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 10.7 GB.

IQuest Coder V1 40B Instruct – a large code‑focused LLM

IQuest Coder V1 40B Instruct is a 39.8 billion‑parameter model built on the llama architecture. It supports a native 128K token context and is optimized for coding tasks. The model is available in multiple GGUF quantizations.

Good at

  • Coding assistance
  • Instruction following
  • Large context handling

Limits

  • No vision support
  • Requires 8K context for memory estimates
  • License is other

Best for

  • Writing code snippets
  • Debugging guidance
  • Code generation for large projects

Who it’s for. Developers and researchers needing a high‑capacity code model. The model is suited for environments that can handle the memory demands of a 40B parameter LLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 3.2 GB
Fits Get file →
IQ1_S8.5 GB 11.7 GB
Too big Get file →
IQ1_M9.3 GB 12.5 GB
Too big Get file →
IQ2_XXS10.7 GB 13.9 GB
Too big Get file →
IQ2_XS11.8 GB 15.0 GB
Too big Get file →
IQ2_S12.3 GB 15.5 GB
Too big Get file →
IQ2_M13.4 GB 16.6 GB
Too big Get file →
Q2_K_S13.7 GB 16.9 GB
Too big Get file →
Q2_K14.8 GB 18.0 GB
Too big Get file →
IQ3_XXS15.4 GB 18.6 GB
Too big Get file →
IQ3_XS16.5 GB 19.6 GB
Too big Get file →
IQ3_S17.4 GB 20.5 GB
Too big Get file →
Q3_K_S17.4 GB 20.5 GB
Too big Get file →
IQ3_M17.8 GB 21.0 GB
Too big Get file →
Q3_K_M19.2 GB 22.4 GB
Too big Get file →
Q3_K_L20.8 GB 24.0 GB
Too big Get file →
IQ4_XS21.3 GB 24.5 GB
Too big Get file →
Q4_022.6 GB 25.8 GB
Too big Get file →
Q4_K_S22.7 GB 25.9 GB
Too big Get file →
Q4_K_M24.0 GB 27.2 GB
Too big Get file →
Q4_125.0 GB 28.1 GB
Too big Get file →
Q5_K_S27.4 GB 30.6 GB
Too big Get file →
Q5_K_M28.2 GB 31.4 GB
Too big Get file →
Q6_K32.6 GB 35.8 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (8.5 GB file, 11.7 GB memory). For 12 GB VRAM, IQ2_XS (11.85 GB file, 15 GB memory). For 16 GB VRAM, Q2_K (14.77 GB file, 18 GB memory). Memory estimates are approximate.

What GPU do you need for 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: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 6 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 8 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 3.2 GB in use).
  • 12 GB VRAM: the best quant that fits is IQ1_S (8.5 GB file, about 11.7 GB in use).
  • 16 GB VRAM: the best quant that fits is IQ2_S (12.3 GB file, about 15.5 GB in use).
  • 24 GB VRAM: the best quant that fits is Q3_K_L (20.8 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is Q5_K_M (28.2 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q6_K (32.6 GB file, about 35.8 GB in use).

Which IQuest Coder V1 40B Instruct quant should you choose?

Q4_K_M is the usual starting point for IQuest Coder V1 40B Instruct: it balances file size and quality well. Here it is a 24.0 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters39.8B
Layers80
Trained context131,072 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyIquest
Licenseother
Downloads (HF)3,083
Last updated2026-01-02

Frequently asked questions about IQuest Coder V1 40B Instruct

How much VRAM does IQuest Coder V1 40B Instruct need?

About 27.2 GB at Q4_K_M with an 8K context window. That is the 24.0 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 IQuest Coder V1 40B Instruct on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 3.2 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of IQuest Coder V1 40B Instruct GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 8.5 GB, IQ1_M is 9.3 GB, IQ2_XXS is 10.7 GB, IQ2_XS is 11.8 GB, IQ2_S is 12.3 GB and 18 more.

What context length does 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 IQuest Coder V1 40B Instruct GGUF?

The files are on Hugging Face in the mradermacher/IQuest-Coder-V1-40B-Instruct-i1-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 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.

Can I run IQuest Coder V1 40B Instruct on 8 GB VRAM?

Use the IQ1_S quant, which requires about 11.7 GB of VRAM at 8K context. It will fit on 8 GB VRAM with careful batching.

Does this model support image input?

No, the model has no vision capabilities.

What is the maximum context length?

The model natively supports up to 128K tokens.

Other GGUFs of IQuest-Coder-V1-40B-Instruct

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Iquest models

All Iquest →

Other large models

All large models →