What are the hardware requirements for Minicpm5 2B Distilled Reasoning?

Minicpm5 2B Distilled Reasoning requires approximately 5 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Minicpm5 2B Distilled Reasoning and how large is it?

Minicpm5 2B Distilled Reasoning is developed by jigs97022, a model with 2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Minicpm5 2B Distilled Reasoning?

Minicpm5 2B Distilled Reasoning is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Minicpm5 2B Distilled Reasoning by jigs97022 — VRAM 5GB, 128K context

Name: Minicpm5 2B Distilled Reasoning
Author: jigs97022

Minicpm5 2B Distilled Reasoning is an open-source language model by jigs97022. Features: 2b LLM, VRAM: 5GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.28.

2b Base model:finetune:openbmb/mi... Base model:openbmb/minicpm5-2b Conversational Distillation En Endpoints compatible Gguf Glm-5.2 Kimi-k3 Llama Llama.cpp Minicpm5 Quantized Qwen3.8-max Reasoning Region:us Safetensors Sft Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/jigs97022/minicpm5-2b-distilled-reasoning

Minicpm5 2B Distilled Reasoning Parameters and Internals

LLM Name	Minicpm5 2B Distilled Reasoning
Repository 🤗	https://huggingface.co/jigs97022/minicpm5-2b-distilled-reasoning
Base Model(s)	MiniCPM5 2B openbmb/MiniCPM5-2B
Model Size	2b
Required VRAM	5 GB
Updated	2026-09-11
Maintainer	jigs97022
Model Type	llama
Model Files	5.0 GB: 0-of-1
Supported Languages	en zh
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Tokenizer Class	TokenizersBackend
Padding Token	<unused_token_477>
Vocabulary Size	130560
Torch Data Type	bfloat16

Rank the Minicpm5 2B Distilled Reasoning capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Minicpm5 2B Distilled Reasoning

Best Alternatives	Context / RAM	Downloads	Likes
MiniCPM5 Pashto Native GGUF	128K / 1.3 GB	322	2
Llama3Ternary 2b	8K / 0.7 GB	1260	0
Aitana 2B S Base	8K / 4.5 GB	559	1
Aitana 2B S Tourism Base	8K / 4.5 GB	221	0
HelpingAI2.5 2B	8K / 1.1 GB	70	2
HelpingAI2.5 2B	8K / 1.1 GB	19	2
Veyra2 30M Base 2B Tokens	1K / 0.1 GB	404	1
MiniCPM5 2B Chat Mlx 4bit	128K / 1.4 GB	232	2
MiniCPM5 2B 8bit	128K / 2.7 GB	734	6
MiniCPM5 2B OptiQ 4bit	128K / 1.9 GB	317	3

Note: green Score (e.g. "73.2") means that the model is better than jigs97022/minicpm5-2b-distilled-reasoning.