LLM EXPLORER 61,755 MODELS INDEXED

Mixtral Instruct AWQ by casperhansen

By casperhansen · 2333 downloads
HF Repo ↗ Copy URL

Mixtral Instruct AWQ is an open-source language model by casperhansen. Features: 46.7b LLM, VRAM: 24.7GB, Context: 32K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.12.

  4-bit   Awq   Conversational   Deploy:azure   Endpoints compatible   Instruct   Mixtral   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/casperhansen/mixtral-instruct-awq 

Mixtral Instruct AWQ Parameters and Internals

Additional Notes 
This is a working version of Mixtral Instruct that is AWQ quantized. The repository is suggested for use as of 11-02-2024, due to another version not working.
LLM NameMixtral Instruct AWQ
Repository 🤗https://huggingface.co/casperhansen/mixtral-instruct-awq 
Model Size46.7b
Required VRAM24.7 GB
Updated2026-08-08
Maintainercasperhansen
Model Typemixtral
Instruction-BasedYes
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   4.7 GB: 3-of-3
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mixtral Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB50
Dolphin 2.7 Mixtral 8x7b AWQ32K / 24.7 GB255023
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB104559
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB124816
...xtral Instruct AWQ Clone Dec2332K / 24.7 GB90
...ixtral Instruct 8x7b Zloss AWQ32K / 24.7 GB02
...0.1 LimaRP ZLoss DARE TIES AWQ32K / 24.7 GB33
...Instruct V0.1 LimaRP ZLoss AWQ32K / 24.7 GB81
...utLM Mixtral 8x7B Instruct AWQ32K / 24.7 GB612
Dolphin 2.6 Mixtral 8x7b AWQ32K / 24.7 GB3212
Note: green Score (e.g. "73.2") means that the model is better than casperhansen/mixtral-instruct-awq.