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

mondk/MiniCPM5-1B-MSH-SFT-GGUF overview

Trained on cleaned datasets. Safetensors: mondk/MiniCPM5 1B MSH SFT SAFETENSORS Datasets: mondk/UltraData SFT 2605 CLEANED mondk/Greetings hi for train Msh v2 …

ggufminicpmmshthinksfttoolcalltext-generationendataset:mondk/UltraData-SFT-2605-CLEANEDdataset:mondk/Greetings-hi-for-train-Msh-v2base_model:mondk/MiniCPM5-1B-MSH-SFT-SAFETENSORSbase_model:quantized:mondk/MiniCPM5-1B-MSH-SFT-SAFETENSORSlicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~850.5 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
177
Likes
1
Pipeline
text-generation
Author

Repository Files & Downloads

1 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
minicpm5-Q6_K.ggufGGUFQ6_K850.5 MBDownload

Model Details

Model IDmondk/MiniCPM5-1B-MSH-SFT-GGUF
Authormondk
Pipelinetext-generation
Licenseapache-2.0
Base modelmondk/MiniCPM5-1B-MSH-SFT-SAFETENSORS
Last modified2026-10-07T10:08:03.000Z

Model README

---

tags:

  • minicpm
  • msh
  • think
  • sft
  • toolcall

license: apache-2.0

datasets:

  • mondk/UltraData-SFT-2605-CLEANED
  • mondk/Greetings-hi-for-train-Msh-v2

language:

  • en

base_model:

  • mondk/MiniCPM5-1B-MSH-SFT-SAFETENSORS

pipeline_tag: text-generation

---

Trained on cleaned datasets.

Safetensors: mondk/MiniCPM5-1B-MSH-SFT-SAFETENSORS

Datasets:

  • mondk/UltraData-SFT-2605-CLEANED
  • mondk/Greetings-hi-for-train-Msh-v2

Improvements:

  • Reduced Chinese language knowledge (prevents the model from switching to another language while conversing in English).

Limitations:

  • Model may be faster due to its lighter weight, but may not be as thoroughly trained as OpenBMB

---

benchmark_here

Based on my benchmarks (results may vary):

| | mondk/MiniCPM5-1B-MSH-SFT | Qwen/Qwen3.5-4B |

| :--- | :---: | :---: |

| Pass rate | 27% | 10% |

| Easy | 2/15 | 2/15 |

| Medium | 9/25 | 2/25 |

| Hard | 5/20 | 2/20 |

| Latency/question | 14.8s | 1.8s |

---

For maximum performance, set temp = 0.8

ty

Run mondk/MiniCPM5-1B-MSH-SFT-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