IQ

IQuest Coder V1 40B Base Stage1

IquestGGUF by mradermacherUpdated 2026-01-03
Download on Hugging Face
Parameters39.8B
Context16K
Layers80
Architecturellama
Smallest quant0.0 GB
Quick answer

IQuest Coder V1 40B Base Stage1 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).

IQuest Coder V1 40B Base Stage1 – a 39.8B parameter code LLM

IQuest Coder V1 40B Base Stage1 is a 39.8B parameter code language model. It supports a native context length of 16384 tokens and is optimized for coding and tool use. The model is part of the Iquest family and is available in multiple GGUF quantizations.

Good at

  • Coding assistance
  • Tool integration
  • Long context handling

Limits

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

Best for

  • Autonomous software engineering
  • Competitive programming
  • Complex tool use

Who it’s for. Developers and researchers who need a large code LLM with native long‑context support. The model is suitable for tasks that require detailed code generation and tool interaction.

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 at 8K context). For 16 GB VRAM, IQ2_M (13.42 GB file, 16.6 GB memory) or Q2_K (14.77 GB file, 18 GB memory). For 24 GB VRAM, Q4_K_M (24.03 GB file, 27.2 GB memory) or Q5_K_S (27.42 GB file, 30.6 GB memory). Estimates are approximate.

What GPU do you need for IQuest Coder V1 40B Base Stage1?

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 Base Stage1 quant should you choose?

Q4_K_M is the usual starting point for IQuest Coder V1 40B Base Stage1: 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 context16,384 tokens
KV cache (fp16)320 KB per token

Source

Quantized bymradermacher
FamilyIquest
Licenseother
Downloads (HF)1,285
Last updated2026-01-03

Frequently asked questions about IQuest Coder V1 40B Base Stage1

How much VRAM does IQuest Coder V1 40B Base Stage1 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 Base Stage1 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 Base Stage1 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 Base Stage1 support?

The GGUF header lists a trained context length of 16,384 tokens (16K). The KV cache grows with the context you use: about 2.7 GB at 8K and 5.4 GB at 16K.

Where can I download IQuest Coder V1 40B Base Stage1 GGUF?

The files are on Hugging Face in the mradermacher/IQuest-Coder-V1-40B-Base-Stage1-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 Base Stage1 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 this model on 8 GB VRAM?

Yes, using the IQ1_S quantization which requires about 11.7 GB memory at 8K context.

Does this model support vision tasks?

No, the model does not include vision capabilities.

What is the native context length of this model?

The model natively supports 16384 tokens of context.

Other GGUFs of IQuest-Coder-V1-40B-Base-Stage1

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Iquest models

All Iquest →

Other large models

All large models →