What are the hardware requirements for MiniCPM 2B RAFT Lora Hotpotqa Dev?

MiniCPM 2B RAFT Lora Hotpotqa Dev requires approximately 5.5 GB of VRAM and supports a context window of 4K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed MiniCPM 2B RAFT Lora Hotpotqa Dev and how large is it?

MiniCPM 2B RAFT Lora Hotpotqa Dev is developed by isaacchung, 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 MiniCPM 2B RAFT Lora Hotpotqa Dev?

MiniCPM 2B RAFT Lora Hotpotqa Dev is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

MiniCPM 2B RAFT Lora Hotpotqa Dev by isaacchung — VRAM 5.5GB, 4K context

Name: MiniCPM 2B RAFT Lora Hotpotqa Dev
Author: isaacchung

MiniCPM 2B RAFT Lora Hotpotqa Dev is an open-source language model by isaacchung. Features: 2b LLM, VRAM: 5.5GB, Context: 4K, License: apache-2.0, LLM Explorer Score: 0.13.

Arxiv:1910.09700 Conversational Custom code Lora Minicpm Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/isaacchung/MiniCPM-2B-RAFT-lora-hotpotqa-dev

MiniCPM 2B RAFT Lora Hotpotqa Dev Parameters and Internals

Additional Notes

Automatically generated model card for a 🤗 transformers model.

Training Details

Data Sources:

isaacchung/hotpotqa-dev-raft-subset

Hardware Used:

1x NVIDIA RTX 6000 Ada

LLM Name	MiniCPM 2B RAFT Lora Hotpotqa Dev
Repository 🤗	https://huggingface.co/isaacchung/MiniCPM-2B-RAFT-lora-hotpotqa-dev
Model Size	2b
Required VRAM	5.5 GB
Updated	2026-07-28
Maintainer	isaacchung
Model Type	minicpm
Model Files	5.0 GB: 1-of-2 0.5 GB: 2-of-2
Model Architecture	MiniCPMForCausalLM
License	apache-2.0
Context Length	4096
Model Max Length	4096
Transformers Version	4.41.2
Tokenizer Class	LlamaTokenizer
Vocabulary Size	122753
LoRA Model	Yes
Torch Data Type	float16

Rank the MiniCPM 2B RAFT Lora Hotpotqa Dev 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 MiniCPM 2B RAFT Lora Hotpotqa Dev

Best Alternatives	Context / RAM	Downloads	Likes
MiniCPM 2B 128K	64K / 6 GB	1905	44
MiniCPM 2B Sft Bf16	4K / 5.5 GB	66563	126
Sparsing Law 0.1B Relu	4K / 0.4 GB	7	2
MiniCPM MoE 8x2B	4K / 27.7 GB	1373	46
MiniCPM Duplex	4K / 5.5 GB	490	6
...iniCPM 2B DPO Bf16 Safetensors	4K / 5.5 GB	75	1
...iniCPM 2B DPO Fp32 Safetensors	4K / 10.9 GB	55	1
...iniCPM 2B Sft Fp32 Safetensors	4K / 10.9 GB	34	1
...iniCPM 2B Sft Fp32 Safetensors	4K / 10.9 GB	7	1
...iniCPM 2B DPO Bf16 Safetensors	4K / 5.5 GB	1	1

Note: green Score (e.g. "73.2") means that the model is better than isaacchung/MiniCPM-2B-RAFT-lora-hotpotqa-dev.