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

Stoned-Code/opusculum-350m-gguf overview

magnum mini gguf : GGUF This model was finetuned and converted to GGUF format using Unsloth https://github.com/unslothai/unsloth . Example usage : For text onl…

ggufgranitemoehybridllama.cppunslothendpoints_compatibleregion:usconversational

Runs locally from ~196.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline

Repository Files & Downloads

6 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
checkpoint-17080.Q2_K_L.ggufGGUFGGUF196.0 MBDownload
checkpoint-17080.Q3_K_M.ggufGGUFGGUF198.7 MBDownload
checkpoint-17080.Q4_K_M.ggufGGUFGGUF226.0 MBDownload
checkpoint-17080.Q5_K_M.ggufGGUFGGUF251.8 MBDownload
checkpoint-17080.Q6_K.ggufGGUFGGUF279.2 MBDownload
checkpoint-17080.Q8_0.ggufGGUFGGUF360.6 MBDownload

Model Details

Model IDStoned-Code/opusculum-350m-gguf
AuthorStoned-Code
Pipeline
License
Base model
Last modified2026-07-20T06:28:15.000Z

Model README

---

tags:

  • gguf
  • llama.cpp
  • unsloth

---

magnum-mini-gguf : GGUF

This model was finetuned and converted to GGUF format using Unsloth.

Example usage:

  • For text only LLMs: llama-cli -hf Stoned-Code/magnum-mini-gguf --jinja
  • For multimodal models: llama-mtmd-cli -hf Stoned-Code/magnum-mini-gguf --jinja

Available Model files:

  • checkpoint-17080.Q8_0.gguf
  • checkpoint-17080.Q6_K.gguf
  • checkpoint-17080.Q5_K_M.gguf
  • checkpoint-17080.Q4_K_M.gguf
  • checkpoint-17080.Q3_K_M.gguf
  • checkpoint-17080.Q2_K_M.gguf

This was trained 2x faster with Unsloth

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>

Run Stoned-Code/opusculum-350m-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