LLM EXPLORER 60,645 MODELS INDEXED

Poemma 12B by 0x7o

By 0x7o · 24 downloads
HF Repo ↗ Copy URL

Poemma 12B is an open-source language model by 0x7o. Features: 12b LLM, VRAM: 24.5GB, Context: 1000K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.15.

  4bit   Conversational   Dataset:0x7o/poemma-10k   Endpoints compatible   Instruct   Mistral   Orpo   Quantized   Region:us   Ru   Safetensors   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/0x7o/poemma-12B 

Poemma 12B Parameters and Internals

LLM NamePoemma 12B
Repository 🤗https://huggingface.co/0x7o/poemma-12B 
Model Size12b
Required VRAM24.5 GB
Updated2026-09-07
Maintainer0x7o
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-5   4.9 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   4.9 GB: 5-of-5
Supported Languagesru
Quantization Type4bit
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length1024000
Model Max Length1024000
Transformers Version4.46.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<pad>
Vocabulary Size131072
Torch Data Typebfloat16

Best Alternatives to Poemma 12B

Best Alternatives
Context / RAM
Downloads
Likes
Geneva 12B GCv2 5M1000K / 24.5 GB2913
ReWiz Nemo 12B Instruct1000K / 24.5 GB62
...o Instruct 12B Philosophy Math1000K / 24.5 GB171
...omix Unleashed 12B V0.6.1 8bit1000K / 12.9 GB42
Ava 1.0 12B1000K / 24.5 GB344
...t RP Noodles 12B V1.4 EXL2 8.01000K / 12.5 GB342
Lumimaid Magnum 12B EXL2 8.01000K / 12.6 GB274
DeepOpus 1 12B Preview128K / 24.5 GB180
DeepNeo 1 12B Preview128K / 24.5 GB150
...r Nemo 12B Instruct R 21 09 241000K / 24.5 GB396277141
Note: green Score (e.g. "73.2") means that the model is better than 0x7o/poemma-12B.