What are the hardware requirements for Sharp MiniCPM5 2B MLX OQ6e?

Sharp MiniCPM5 2B MLX OQ6e requires approximately 2.1 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 Sharp MiniCPM5 2B MLX OQ6e and how large is it?

Sharp MiniCPM5 2B MLX OQ6e is developed by peculiar-ragdoll, 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 Sharp MiniCPM5 2B MLX OQ6e?

Sharp MiniCPM5 2B MLX OQ6e is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Sharp MiniCPM5 2B MLX OQ6e by peculiar-ragdoll — VRAM 2.1GB, 128K context

Name: Sharp MiniCPM5 2B MLX OQ6e
Author: peculiar-ragdoll

Sharp MiniCPM5 2B MLX OQ6e is an open-source language model by peculiar-ragdoll. Features: 2b LLM, VRAM: 2.1GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.32.

6-bit Apple-silicon Base model:openbmb/minicpm5-2b Base model:quantized:openbmb/m... Coding Conversational En Imatrix Llama Long-context Minicpm Mlx Omlx Oq Region:us Safetensors Sharp-template Zh

Model Card on HF 🤗: https://huggingface.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e

Sharp MiniCPM5 2B MLX OQ6e Parameters and Internals

LLM Name	Sharp MiniCPM5 2B MLX OQ6e
Repository 🤗	https://huggingface.co/peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e
Base Model(s)	MiniCPM5 2B openbmb/MiniCPM5-2B
Model Size	2b
Required VRAM	2.1 GB
Updated	2026-10-01
Maintainer	peculiar-ragdoll
Model Type	llama
Model Files	2.1 GB
Supported Languages	en zh
Model Architecture	LlamaForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	5.6.2
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	</s>
Vocabulary Size	130560
Torch Data Type	bfloat16

Rank the Sharp MiniCPM5 2B MLX OQ6e 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 Sharp MiniCPM5 2B MLX OQ6e

Best Alternatives	Context / RAM	Downloads	Likes
MiniCPM5 2B Base	512K / 5 GB	54	17
MiniCPM5 2B	128K / 5 GB	2879	623
Xor Lite	128K / 5 GB	484	3
Huihui MiniCPM5 2B Abliterated	128K / 5 GB	1227	14
Pjev 2B	128K / 5 GB	356	1
...iniCPM5 2B RotSVDMix Quantized	128K / 2 GB	1389	1
MiniCPM5 2B MLX	128K / 1.4 GB	288	24
BananaMind CodeQ 1.3 2B	128K / 5.1 GB	663	3
Abliterated Minicpm5 2B V3	128K / 5 GB	554	0
...iniCPM5 2B SFT Pashto Instruct	128K / 5 GB	1076	0

Note: green Score (e.g. "73.2") means that the model is better than peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e.