LLM EXPLORER 60,645 MODELS INDEXED

Openchat 3.5 0106 128K 4.0bpw H6 EXL2 by LoneStriker

By LoneStriker · 4 downloads
HF Repo ↗ Copy URL

Openchat 3.5 0106 128K 4.0bpw H6 EXL2 is an open-source language model by LoneStriker. Features: 7b LLM, VRAM: 3.9GB, Context: 128K, License: apache-2.0, Quantized, LLM Explorer Score: 0.1.

  Arxiv:2303.08774   Arxiv:2309.11235 Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   C-rlft   Conversational   Endpoints compatible   Exl2   Mistral   Openchat   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/LoneStriker/openchat-3.5-0106-128k-4.0bpw-h6-exl2 

Openchat 3.5 0106 128K 4.0bpw H6 EXL2 Parameters and Internals

Model Type 
text-generation
LLM NameOpenchat 3.5 0106 128K 4.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/openchat-3.5-0106-128k-4.0bpw-h6-exl2 
Base Model(s)  mistralai/Mistral-7B-v0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM3.9 GB
Updated2026-08-01
MaintainerLoneStriker
Model Typemistral
Model Files  3.9 GB
Quantization Typeexl2
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length131072
Model Max Length131072
Transformers Version4.37.0.dev0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32002
Torch Data Typebfloat16

Best Alternatives to Openchat 3.5 0106 128K 4.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...t 3.5 0106 128K 8.0bpw H8 EXL2128K / 7.4 GB11
...aude Sonnet Mistral 7B It V0.332K / 14.5 GB72
Mistral 7B V0.3 Bnb 4bit32K / 4.1 GB38132322
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB791
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB3463342
Mistral 7B Instruct V0.2 8bit32K / 7.6 GB51
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB716035
Mixtral V0.3 Full 16bit32K / 14.5 GB80
... 7B Instruct V0.3ContinuedFine32K / 14.5 GB140
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/openchat-3.5-0106-128k-4.0bpw-h6-exl2.