Mixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2 by FuturisticVibes

 ยป  All LLMs  ยป  FuturisticVibes  ยป  Mixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2   URL Share it on

  8-bit   Autotrain compatible   Conversational   De   En   Endpoints compatible   Es   Exl2   Fr   Instruct   It   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Mixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2 (FuturisticVibes/Mixtral-8x22B-Instruct-v0.1-8.0bpw-h8-exl2)

Mixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2 Parameters and Internals

Model Type 
Large Language Model, Instruct fine-tuned
Additional Notes 
Includes a measurement.json file for further quantization. This release marks the last of the BIG Mixtrals.
Supported Languages 
en (high), es (high), it (high), de (high), fr (high)
LLM NameMixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2
Repository ๐Ÿค—https://huggingface.co/FuturisticVibes/Mixtral-8x22B-Instruct-v0.1-8.0bpw-h8-exl2 
Required VRAM120.2 GB
Updated2025-01-14
MaintainerFuturisticVibes
Model Typemixtral
Instruction-BasedYes
Model Files  8.6 GB: 1-of-15   8.5 GB: 2-of-15   8.6 GB: 3-of-15   8.5 GB: 4-of-15   8.6 GB: 5-of-15   8.6 GB: 6-of-15   8.6 GB: 7-of-15   8.5 GB: 8-of-15   8.5 GB: 9-of-15   8.6 GB: 10-of-15   8.6 GB: 11-of-15   8.6 GB: 12-of-15   8.5 GB: 13-of-15   8.6 GB: 14-of-15   0.3 GB: 15-of-15
Supported Languagesen es it de fr
Quantization Typeexl2
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length65536
Model Max Length65536
Transformers Version4.38.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32768
Torch Data Typebfloat16

Best Alternatives to Mixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...M 2 8x22B Beige 3.0bpw H6 EXL264K / 53.2 GB190
...M 2 8x22B Beige 4.0bpw H6 EXL264K / 70.8 GB190
...M 2 8x22B Beige 2.4bpw H6 EXL264K / 42.7 GB170
...M 2 8x22B Beige 5.0bpw H6 EXL264K / 88.5 GB170
...8x22b Instruct Oh EXL2 2.25bpw64K / 40.1 GB61
...eryTour V2 8x7B 4.5bpw H6 EXL232K / 26.5 GB62
...it MoE 2bitgs8 Metaoffload HQQ32K / 24.1 GB1020
... 4bit MoE 3bit Metaoffload HQQ32K / 22.4 GB813
...hin 2.7 Mixtral 8x7b 8bpw EXL232K / 46.8 GB92
... 4bit MoE 2bit Metaoffload HQQ32K / 18.3 GB1215
Note: green Score (e.g. "73.2") means that the model is better than FuturisticVibes/Mixtral-8x22B-Instruct-v0.1-8.0bpw-h8-exl2.

Rank the Mixtral 8x22B Instruct V0.1 8.0bpw H8 EXL2 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 41301 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227