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

Mixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ by mobiuslabsgmbh

 »  All LLMs  »  mobiuslabsgmbh  »  Mixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ   URL Share it on

  11   
  4bit   Autotrain compatible   Conversational   Instruct   Mixtral   Moe   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ 

Mixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ Benchmarks

LLME Score: 0.18146
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ (mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ)

Mixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ Parameters and Internals

Model Type 
text-generation
Additional Notes 
This model uses Half-Quadratic Quantization (HQQ) for quantizing attention layers to 4-bit and experts to 2-bit, enabling a significant reduction in VRAM usage.
LLM NameMixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ
Repository 🤗https://huggingface.co/mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ 
Required VRAM24.1 GB
Updated2024-12-26
Maintainermobiuslabsgmbh
Model Typemixtral
Instruction-BasedYes
Model Files  24.1 GB
Quantization Type4bit
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ

Best Alternatives
Context / RAM
Downloads
Likes
...M 2 8x22B Beige 2.4bpw H6 EXL264K / 42.7 GB160
...M 2 8x22B Beige 3.0bpw H6 EXL264K / 53.2 GB160
...M 2 8x22B Beige 4.0bpw H6 EXL264K / 70.8 GB140
...M 2 8x22B Beige 5.0bpw H6 EXL264K / 88.5 GB100
...B Instruct V0.1 8.0bpw H8 EXL264K / 120.2 GB81
...8x22b Instruct Oh EXL2 2.25bpw64K / 40.1 GB101
...eryTour V2 8x7B 4.5bpw H6 EXL232K / 26.5 GB122
... 4bit MoE 3bit Metaoffload HQQ32K / 22.4 GB813
...hin 2.7 Mixtral 8x7b 8bpw EXL232K / 46.8 GB142
... 4bit MoE 2bit Metaoffload HQQ32K / 18.3 GB615
Note: green Score (e.g. "73.2") means that the model is better than mobiuslabsgmbh/Mixtral-8x7B-Instruct-v0.1-hf-attn-4bit-moe-2bitgs8-metaoffload-HQQ.

Rank the Mixtral 8x7B Instruct V0.1 Hf Attn 4bit MoE 2bitgs8 Metaoffload HQQ 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? 40303 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.
Release v20241227
  Support LLM Explorer