MiniCPM MoE 8x2B is an open-source language model by openbmb. Features: 2b LLM, VRAM: 27.7GB, Context: 4K, MoE, LLM Explorer Score: 0.13.
| Model Type |
| |
| Additional Notes |
|
| LLM Name | MiniCPM MoE 8x2B |
| Repository 🤗 | https://huggingface.co/openbmb/MiniCPM-MoE-8x2B |
| Model Size | 2b |
| Required VRAM | 27.7 GB |
| Updated | 2026-07-04 |
| Maintainer | openbmb |
| Model Files | |
| Model Architecture | MiniCPMForCausalLM |
| Context Length | 4096 |
| Model Max Length | 4096 |
| Transformers Version | 4.36.0 |
| Tokenizer Class | LlamaTokenizer |
| Vocabulary Size | 122753 |
| Torch Data Type | bfloat16 |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| MiniCPM 2B 128K | 64K / 6 GB | 1905 | 44 |
| MiniCPM 2B Sft Bf16 | 4K / 5.5 GB | 73860 | 126 |
| Sparsing Law 0.1B Relu | 4K / 0.4 GB | 413 | 2 |
| MiniCPM Duplex | 4K / 5.5 GB | 617 | 6 |
| ...iCPM 2B RAFT Lora Hotpotqa Dev | 4K / 5.5 GB | 5 | 0 |
| MiniCPM 2B Sft Fp32 | 4K / 10.9 GB | 566 | 297 |
| MiniCPM 2B DPO Bf16 | 4K / 5.5 GB | 1897 | 52 |
| ...iniCPM 2B DPO Bf16 Safetensors | 4K / 5.5 GB | 206 | 1 |
| ...iniCPM 2B DPO Fp32 Safetensors | 4K / 10.9 GB | 34 | 1 |
| ...iniCPM 2B Sft Fp32 Safetensors | 4K / 10.9 GB | 14 | 1 |
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟