Qwen3 Next 80B A3B Instruct 8bit by mlx-community

 ยป  All LLMs  ยป  mlx-community  ยป  Qwen3 Next 80B A3B Instruct 8bit   URL Share it on

  8-bit   8bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-next-80b...   Conversational   Instruct   Mlx   Quantized   Qwen3 next   Region:us   Safetensors   Sharded   Tensorflow

Qwen3 Next 80B A3B Instruct 8bit Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen3 Next 80B A3B Instruct 8bit (mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit)
๐ŸŒŸ Advertise your project ๐Ÿš€

Qwen3 Next 80B A3B Instruct 8bit Parameters and Internals

LLM NameQwen3 Next 80B A3B Instruct 8bit
Repository ๐Ÿค—https://huggingface.co/mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit 
Base Model(s)  Qwen3 Next 80B A3B Instruct   Qwen/Qwen3-Next-80B-A3B-Instruct
Model Size80b
Required VRAM83.9 GB
Updated2025-09-17
Maintainermlx-community
Model Typeqwen3_next
Instruction-BasedYes
Model Files  5.0 GB: 1-of-17   5.2 GB: 2-of-17   5.2 GB: 3-of-17   5.2 GB: 4-of-17   5.2 GB: 5-of-17   5.2 GB: 6-of-17   5.2 GB: 7-of-17   5.2 GB: 8-of-17   5.2 GB: 9-of-17   5.2 GB: 10-of-17   5.2 GB: 11-of-17   5.2 GB: 12-of-17   5.2 GB: 13-of-17   5.2 GB: 14-of-17   5.2 GB: 15-of-17   5.2 GB: 16-of-17   0.9 GB: 17-of-17
Quantization Type8bit
Model ArchitectureQwen3NextForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen3 Next 80B A3B Instruct 8bit

Best Alternatives
Context / RAM
Downloads
Likes
...en3 Next 80B A3B Instruct 4bit256K / 44.9 GB463212
...Next 80B A3B Instruct Bnb 4bit256K / 42.1 GB333210
...3 Next 80B A3B Instruct Q2 Mlx256K / 24.9 GB23955
Qwen3 Next 80B A3B Instruct256K / 162.7 GB304748608
Qwen3 Next 80B A3B Instruct256K / 162.7 GB232770
...Next 80B A3B Instruct AWQ 4bit256K / 47.5 GB3392121
...t 80B A3B Instruct FP8 Dynamic256K / 80.5 GB75233
...ext 80B A3B Instruct Mxfp4 Mlx256K / 42 GB27135
... Instruct Int4 Mixed AutoRound256K / 43.1 GB7226
...0B A3B Instruct Int4 AutoRound256K / 42.3 GB416
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit.

Rank the Qwen3 Next 80B A3B Instruct 8bit 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? 51415 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124