Back to Models
iquestlabProprietary

IQuest-Coder-V1-40B-Instruct

IQuest-Coder-V1-40B-Instruct is a programming-specialized foundation model developed by iquestlab. It boasts approximately 400B parameters and supports a maximum long context window of 128K.

Parameters

400.0B

Context Window

128K

License

https://github.com/openai/gpt-2/blob/master/LICENSE

Release Date

2026-01-01

API Pricing

API pricing for this model is not yet available

Strengths

  • Extremely large 400B parameters
  • Long 128K context support
  • Powerful coding capabilities

Weaknesses

  • Huge ~80GB file size
  • High hardware requirements
  • Closed-source license restrictions

Use Cases

  • Analyzing large codebases
  • Complex software development
  • Advanced programming assistance

Deep Analysis

Architecture

Dense Transformer (40B, 80 layers)

Code-specialized LLM

Context Window

128K tokens

Native long context

Release Date

March 2026

License

Custom

GitHub Stars

1378

IQuestLab/IQuest-Coder-V1

Family

7B/14B/40B/40B-Loop

Multiple size variants

Key Feature

Code-Flow Training Paradigm

Learns from repo evolution patterns

Strengths

  • SOTA on SWE-Bench Verified, BigCodeBench, LiveCodeBench v6
  • Code-Flow training from repository evolution patterns
  • Multiple size variants (7B/14B/40B)
  • CLI agent integration (ClaudeCode, OpenCode)
  • HTML/SVG generation capability
  • 128K native context

Weaknesses

  • Custom license limits some uses
  • Newer model with less community tooling
  • Code-specialized, less general-purpose

Competitor Comparison

ModelArenaSWEGPQAPrice
DeepSeek Coder V2---Free (open)
CodeLlama 70B---Free (open)
Claude Sonnet 4.6---Paid

IQuest-Coder-V1-40B is iquestlab's code-specialized LLM family with 7B/14B/40B variants. It introduces a Code-Flow training paradigm that learns from repository evolution patterns, achieving SOTA on major coding benchmarks with CLI agent integration.

Analysis generated: 2026-05-24