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…
Runs locally from ~196.0 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
6 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| checkpoint-17080.Q2_K_L.gguf | GGUF | GGUF | 196.0 MB | Download |
| checkpoint-17080.Q3_K_M.gguf | GGUF | GGUF | 198.7 MB | Download |
| checkpoint-17080.Q4_K_M.gguf | GGUF | GGUF | 226.0 MB | Download |
| checkpoint-17080.Q5_K_M.gguf | GGUF | GGUF | 251.8 MB | Download |
| checkpoint-17080.Q6_K.gguf | GGUF | GGUF | 279.2 MB | Download |
| checkpoint-17080.Q8_0.gguf | GGUF | GGUF | 360.6 MB | Download |
Model Details
| Model ID | Stoned-Code/opusculum-350m-gguf |
|---|---|
| Author | Stoned-Code |
| Pipeline | — |
| License | — |
| Base model | — |
| Last modified | 2026-07-20T06:28:15.000Z |
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.ggufcheckpoint-17080.Q6_K.ggufcheckpoint-17080.Q5_K_M.ggufcheckpoint-17080.Q4_K_M.ggufcheckpoint-17080.Q3_K_M.ggufcheckpoint-17080.Q2_K_M.gguf
This was trained 2x faster with Unsloth
Run Stoned-Code/opusculum-350m-gguf with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models