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

Mixtral 8x7b AQLM 2Bit 1x16 Hf by ISTA-DASLab

 »  All LLMs  »  ISTA-DASLab  »  Mixtral 8x7b AQLM 2Bit 1x16 Hf   URL Share it on

  82   

Mixtral 8x7b AQLM 2Bit 1x16 Hf is an open-source language model by ISTA-DASLab. Features: 6.5b LLM, VRAM: 13.1GB, Context: 32K, MoE, Quantized, LLM Explorer Score: 0.12.

  Arxiv:2401.06118   2bit   Aqlm   Endpoints compatible   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf 

Mixtral 8x7b AQLM 2Bit 1x16 Hf Benchmarks

LLME Score: 0.11771
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral 8x7b AQLM 2Bit 1x16 Hf (ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf)
🌟 Advertise your project 🚀

Mixtral 8x7b AQLM 2Bit 1x16 Hf Parameters and Internals

Additional Notes 
This quantization uses 1 codebook of 16 bits.
LLM NameMixtral 8x7b AQLM 2Bit 1x16 Hf
Repository 🤗https://huggingface.co/ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf 
Model Size6.5b
Required VRAM13.1 GB
Updated2026-04-25
MaintainerISTA-DASLab
Model Typemixtral
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   3.1 GB: 3-of-3
Quantization Type2bit
Model ArchitectureMixtralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.38.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mixtral 8x7b AQLM 2Bit 1x16 Hf

Best Alternatives
Context / RAM
Downloads
Likes
...nstruct V0.1 AQLM 2Bit 1x16 Hf32K / 13.1 GB1719
...QLM 2Bit 1x16 Hf Test Dispatch32K / 13.1 GB1013
Mixtral Debug32K / 0 GB140
Mixtral Debug32K / 0 GB60
...kaLM Mixtral 8x7B V0.2 DPO AWQ32K / 24.7 GB60
Taiwan LLM 8x7B DPO AWQ32K / 24.7 GB71
...Hermes 2 Mixtral 8x7B DPO GPTQ32K / 24.7 GB121
...x7B V0.1 OmniQuantv2 W4a16g12832K / 24.7 GB71
...uct V0.1 OmniQuantv1 W4a16g12832K / 24.7 GB51
Note: green Score (e.g. "73.2") means that the model is better than ISTA-DASLab/Mixtral-8x7b-AQLM-2Bit-1x16-hf.

Rank the Mixtral 8x7b AQLM 2Bit 1x16 Hf 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? 53858 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