Model Intelligence Sheet
mondk/MiniCPM5-MSH-2B-IT-GGUF overview
base model: openbmb/MiniCPM5 2B Midtrain GGUF: mondk/MiniCPM5 MSH 2B IT GGUF datasets: mondk/Msh CoT Sft Improvements: Step by step reasoning imitation model L…
Runs locally from ~1.65 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
1 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| Msh-minicpm-Q5_K_S.gguf | GGUF | Q5_K_S | 1.65 GB | Download |
Model Details
| Model ID | mondk/MiniCPM5-MSH-2B-IT-GGUF |
|---|---|
| Author | mondk |
| Pipeline | text-generation |
| License | apache-2.0 |
| Base model | mondk/MiniCPM5-MSH-2B-IT-SAFETENSORS |
| Last modified | 2026-10-10T08:50:38.000Z |
Model README
---
language:
- en
- zh
license: apache-2.0
library_name: transformers
pipeline_tag: text-generation
base_model:
- mondk/MiniCPM5-MSH-2B-IT-SAFETENSORS
datasets:
- mondk/Msh-CoT-Sft
tags:
- minicpm
- msh
- it
- tool-calling
---
base_model: openbmb/MiniCPM5-2B-Midtrain
GGUF: mondk/MiniCPM5-MSH-2B-IT-GGUF
datasets: mondk/Msh-CoT-Sft
Improvements:
- Step-by-step reasoning imitation model
Limitations:
- The model occasionally has formatting errors with
</think>
---
benchmark_here
ty
Run mondk/MiniCPM5-MSH-2B-IT-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models