LLM EXPLORER 66,704 MODELS INDEXED

MiniCPM5 2B GPTQ by openbmb

By openbmb · 82 downloads
HF Repo ↗ Copy URL

MiniCPM5 2B GPTQ is an open-source language model by openbmb. Features: 2b LLM, VRAM: 2.1GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.26.

  Arxiv:2506.07900   Arxiv:2602.09003   4-bit   Awq   Conversational   Dataset:openbmb/ultra-fineweb Dataset:openbmb/ultra-fineweb-...   Dataset:openbmb/ultradata-code   Dataset:openbmb/ultradata-math Dataset:openbmb/ultradata-rl-2... Dataset:openbmb/ultradata-sft-... Dataset:openbmb/ultradata-sft-...   Dataset:openbmb/ultrax-preview   Edge-ai   En   Endpoints compatible   Gptq   Llama   Long-context   Minicpm   Minicpm5   On-device   Quantized   Region:us   Safetensors   Tool-calling   Zh
Model Card on HF 🤗: https://huggingface.co/openbmb/MiniCPM5-2B-GPTQ 

MiniCPM5 2B GPTQ Parameters and Internals

LLM NameMiniCPM5 2B GPTQ
Repository 🤗https://huggingface.co/openbmb/MiniCPM5-2B-GPTQ 
Model Size2b
Required VRAM2.1 GB
Updated2026-09-09
Maintaineropenbmb
Model Typellama
Model Files  2.1 GB
Supported Languagesen zh
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version5.16.1
Tokenizer ClassPreTrainedTokenizerFast
Padding Token</s>
Vocabulary Size130560
Torch Data Typefloat16

Best Alternatives to MiniCPM5 2B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...etune 16bit Wiki 250 Ver2 GPTQ8K / 5.8 GB50
MiniCPM5 2B Chat Mlx 4bit128K / 1.4 GB2322
MiniCPM5 2B 8bit128K / 2.7 GB7346
MiniCPM5 2B OptiQ 4bit128K / 1.9 GB3173
MiniCPM5 2B Mlx 4Bit128K / 1.4 GB2861
MiniCPM5 2B MLX 8bit128K / 2.7 GB1933
MiniCPM5 2B MLX 6bit128K / 2 GB1921
MiniCPM5 2B MLX 4bit128K / 1.4 GB1162
...ll Slm 2B Safetensors Mlx 4Bit8K / 1 GB2674
MiniCPM5 2B Base512K / 5 GB5417
Note: green Score (e.g. "73.2") means that the model is better than openbmb/MiniCPM5-2B-GPTQ.