LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Mistral 7B Instruct V0.2 8bit by LsTam

 »  All LLMs  »  LsTam  »  Mistral 7B Instruct V0.2 8bit   URL Share it on

  4   

Mistral 7B Instruct V0.2 8bit is an open-source language model by LsTam. Features: 7b LLM, VRAM: 7.6GB, Context: 32K, Quantized, Instruction-Based, HF Score: 61.2, LLM Explorer Score: 0.23, ELO: 1072, Arc: 56.7, HellaSwag: 80.8, MMLU: 59.1, TruthfulQA: 55.9, WinoGrande: 77.1, GSM8K: 37.6.

  Arxiv:2310.06825   8-bit   8bit   Bitsandbytes   Endpoints compatible   Instruct   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/LsTam/Mistral-7B-Instruct-v0.2-8bit 

Mistral 7B Instruct V0.2 8bit Benchmarks

LMSys ELO: 1072 vs 1272 (so35)-15.7%
ARC: 56.74 vs 96.7 (so35)-41.3%
HellaSwag: 80.82 vs 95.3 (gpt4)-15.2%
MMLU: 59.1 vs 88.3 (so35)-33.1%
TruthfulQA: 55.86 vs 59 (gpt4)-5.3%
WinoGrande: 77.11 vs 87.5 (gpt4)-11.9%
GSM8K: 37.6 vs 96.4 (so35)-61%
LLME Score: 0.23342
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral 7B Instruct V0.2 8bit (LsTam/Mistral-7B-Instruct-v0.2-8bit)
🌟 Advertise your project 🚀

Mistral 7B Instruct V0.2 8bit Parameters and Internals

Model Type 
8bit quantized
Additional Notes 
The model is loaded in 8bit with `torch_dtype=torch.float16`.
Input Output 
Accepted Modalities:
text
Performance Tips:
Use `use_flash_attention_2=True` for improved performance.
LLM NameMistral 7B Instruct V0.2 8bit
Repository 🤗https://huggingface.co/LsTam/Mistral-7B-Instruct-v0.2-8bit 
Base Model(s)  lachiewyoung/mistral-7b-instruct-1.58bit   lachiewyoung/mistral-7b-instruct-1.58bit
Model Size7b
Required VRAM7.6 GB
Updated2026-04-08
MaintainerLsTam
Model Typemistral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   2.6 GB: 2-of-2
Quantization Type8bit
Model ArchitectureMistralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.35.2
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mistral 7B Instruct V0.2 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.2 Fp1632K / 14.4 GB260
Mistral 7B Instruct V0.2 4bit32K / 4.3 GB1331
...tral 7B Instruct V0.3 Bnb 4bit32K / 4.1 GB3043728
...tral 7B Instruct V0.2 Bnb 4bit32K / 4.1 GB1275236
Mixtral V0.3 Full 16bit32K / 14.5 GB60
Mistral 7B Instruct V0.3 4bit32K / 4.1 GB250538
... 7B Instruct V0.3ContinuedFine32K / 14.5 GB130
...eMistral 7B Instruct Ead 16bit32K / 14.5 GB380
NaturalLM 7B Instruct32K / 14.5 GB1510
MistralContinuedFine32K / 14.5 GB50
Note: green Score (e.g. "73.2") means that the model is better than LsTam/Mistral-7B-Instruct-v0.2-8bit.

Rank the Mistral 7B Instruct V0.2 8bit Capabilities

🆘 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! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 53185 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer