GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

Dzluck/GRM-Coder-14b-GGUF overview

<p align="center" <img src="https://cdn uploads.huggingface.co/production/uploads/685ea8ff7b4139b6845ce395/YF0kEDYMGJhcM3Lbl2EOD.png" alt="logo" width="250" </…

transformersggufqwen3codetext-generationsafetensorsbase_model:Qwen/Qwen3-14Bbase_model:quantized:Qwen/Qwen3-14Blicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~8.38 GB disk (12 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
text-generation
Author

Repository Files & Downloads

5 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
GRM-Coder-14b-F16.ggufGGUFF1627.51 GBDownload
GRM-Coder-14b-Q4_K_M.ggufGGUFQ4_K_M8.38 GBDownload
GRM-Coder-14b-Q5_K_M.ggufGGUFQ5_K_M9.79 GBDownload
GRM-Coder-14b-Q6_K.ggufGGUFQ6_K11.29 GBDownload
GRM-Coder-14b-Q8_0.ggufGGUFQ8_014.62 GBDownload

Model Details

Model IDDzluck/GRM-Coder-14b-GGUF
AuthorDzluck
Pipelinetext-generation
Licenseapache-2.0
Base modelQwen/Qwen3-14B
Last modified2026-08-08T05:57:07.000Z

Model README

---

license: apache-2.0

base_model:

  • Qwen/Qwen3-14B

pipeline_tag: text-generation

library_name: transformers

tags:

  • qwen3
  • code
  • text-generation
  • safetensors

---

<p align="center">

<img src="https://cdn-uploads.huggingface.co/production/uploads/685ea8ff7b4139b6845ce395/YF0kEDYMGJhcM3Lbl2EOD.png" alt="logo" width="250">

</p>

<p align="center"><b>A powerful 14B coding model designed for competitive programming.</b></p>

---

This is quantized version of OrionLLM/GRM-Coder-14b created using llama.cpp

This is a coding model based on Qwen3-14B for competitive programming.

On LiveCodeBench v6 (08/01/2024 - 05/01/2025), we achieve a Pass@1 accuracy of 67.87%, up 7.08% from the baseline Pass@1 accuracy of 60.79% of Qwen3-14B.

We trained on 24k verifiable coding problems over the course of four days.

---

!benchmarks

Run Dzluck/GRM-Coder-14b-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models