LLM Name | Qwen3 Next 80B A3B Instruct 8bit |
Repository ๐ค | https://huggingface.co/mlx-community/Qwen3-Next-80B-A3B-Instruct-8bit |
Base Model(s) | |
Model Size | 80b |
Required VRAM | 83.9 GB |
Updated | 2025-09-23 |
Maintainer | mlx-community |
Model Type | qwen3_next |
Instruction-Based | Yes |
Model Files | |
Quantization Type | 8bit |
Model Architecture | Qwen3NextForCausalLM |
License | apache-2.0 |
Context Length | 262144 |
Model Max Length | 262144 |
Transformers Version | 4.57.0.dev0 |
Tokenizer Class | Qwen2Tokenizer |
Padding Token | <|endoftext|> |
Vocabulary Size | 151936 |
Torch Data Type | bfloat16 |
Errors | replace |
Best Alternatives |
Context / RAM |
Downloads |
Likes |
---|---|---|---|
...Next 80B A3B Instruct Bnb 4bit | 256K / 42.1 GB | 17459 | 12 |
...en3 Next 80B A3B Instruct 4bit | 256K / 44.9 GB | 5533 | 14 |
...3 Next 80B A3B Instruct Q2 Mlx | 256K / 24.9 GB | 3026 | 5 |
Qwen3 Next 80B A3B Instruct | 256K / 162.7 GB | 901498 | 713 |
...Next 80B A3B Instruct AWQ 4bit | 256K / 47.5 GB | 86624 | 26 |
Qwen3 Next 80B A3B Instruct | 256K / 162.7 GB | 3126 | 73 |
... Instruct Int4 Mixed AutoRound | 256K / 43.1 GB | 7563 | 14 |
...t 80B A3B Instruct FP8 Dynamic | 256K / 80.5 GB | 23692 | 4 |
...ext 80B A3B Instruct Mxfp4 Mlx | 256K / 42 GB | 3321 | 5 |
...0B A3B Instruct Int4 AutoRound | 256K / 42.3 GB | 1126 | 7 |
๐ 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! ๐