LLM EXPLORER 60,277 MODELS INDEXED

Autogen Mistral 16bit Merged by lukaskellerstein

By lukaskellerstein · 143 downloads
HF Repo ↗ Copy URL

Autogen Mistral 16bit Merged is an open-source language model by lukaskellerstein. Features: 7.2b LLM, VRAM: 14.5GB, Context: 32K, Quantized, LLM Explorer Score: 0.13.

  Arxiv:1910.09700   16bit   Conversational   Endpoints compatible   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/lukaskellerstein/autogen-mistral-16bit-merged 

Autogen Mistral 16bit Merged Parameters and Internals

LLM NameAutogen Mistral 16bit Merged
Repository 🤗https://huggingface.co/lukaskellerstein/autogen-mistral-16bit-merged 
Model Size7.2b
Required VRAM14.5 GB
Updated2026-08-08
Maintainerlukaskellerstein
Model Typemistral
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3   14.5 GB
Quantization Type16bit
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version5.13.0
Tokenizer ClassTokenizersBackend
Padding Token<pad>
Vocabulary Size32769
Torch Data Typebfloat16

Best Alternatives to Autogen Mistral 16bit Merged

Best Alternatives
Context / RAM
Downloads
Likes
...Sft Bnb 4bit DPO Mtbr 180steps32K / 14.4 GB50
...Sft Bnb 4bit DPO Mtbc 213steps32K / 14.4 GB50
...Sft Bnb 4bit DPO Mtbo 180steps32K / 14.4 GB60
Mixtral V0.3 Full 16bit V232K / 14.5 GB60
...88 07.02 RP DPO Merged 16bit 332K / 14.4 GB250
Rezephyr DPO32K / 14.4 GB200
Zephyr DPO V232K / 14.4 GB191
Tools Mistral 16bit Merged New32K / 14.5 GB50
AI Tutor32K / 14.5 GB60
...Web AI HumanAI 012 INSTRUCT XA512K / 14.4 GB90
Note: green Score (e.g. "73.2") means that the model is better than lukaskellerstein/autogen-mistral-16bit-merged.