IQuestLab/IQuest-Coder-V1 resource

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1389 stars · 98 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

IQuest-Coder-V1 is a family of open code large language models (7B, 14B, and 40B variants including Base, Instruct, and Thinking versions) released on Hugging Face. The models are trained with a code-flow multi-stage paradigm and optimized for autonomous software engineering, tool use, CLI coding agents, and HTML/SVG generation with 128K context.

Use cases

• run a local code LLM for code generation
• power a CLI coding agent like Claude Code or OpenCode with an open model
• generate HTML and SVG from natural language prompts
• fine-tune or build on top of open code model weights
• use a reasoning/thinking model for complex software engineering tasks
• self-host a code assistant with 128K context window

When to choose

• you need open-weight code LLMs in 7B-40B sizes for local or self-hosted inference
• you want models specifically tuned for agentic coding and tool use
• you need long-context (128K) code understanding and generation
• you want both base weights for fine-tuning and instruct/thinking variants for direct use

When to avoid

• you need a managed API service rather than self-hosted model weights
• you require a permissive license - the license is listed as NOASSERTION so verify terms first
• you need non-coding general-purpose chat models
• you lack GPU hardware to run 14B-40B parameter models

Facets

dataset · maturity active

llm-inference machine-learning agent-framework prompt-engineering large-language-models artificial-intelligence developer-tools python cross-platform code-llm model-weights hugging-face cli-agents thinking-models 128k-context code-generation ai-agents gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="IQuestLab/IQuest-Coder-V1")