LLM EXPLORER 61,405 MODELS INDEXED

MIST 1 70B MLX by mlx-community

By mlx-community · 16 downloads
HF Repo ↗ Copy URL

MIST 1 70B MLX is an open-source language model by mlx-community. Features: 70b LLM, VRAM: 140.2GB, Context: 128K, License: llama3.1, Instruction-Based, LLM Explorer Score: 0.24.

Base model:deepseek-ai/deepsee... Base model:merge:deepseek-ai/d... Base model:merge:meta-llama/ll... Base model:merge:nousresearch/... Base model:merge:nvidia/llama-... Base model:meta-llama/llama-3.... Base model:nousresearch/hermes... Base model:nvidia/llama-3.1-ne...   Conversational   Dare ties   En   Endpoints compatible   Instruct   Llama   Llama-3.1   Merge   Mist   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/MIST-1-70B-MLX 

MIST 1 70B MLX Parameters and Internals

LLM NameMIST 1 70B MLX
Repository 🤗https://huggingface.co/mlx-community/MIST-1-70B-MLX 
Base Model(s)  nvidia/Llama-3.1-Nemotron-70B-Instruct-HF   DeepSeek R1 Distill Llama 70B   NousResearch/Hermes-3-Llama-3.1-70B   meta-llama/Llama-3.1-70B-Instruct   nvidia/Llama-3.1-Nemotron-70B-Instruct-HF   deepseek-ai/DeepSeek-R1-Distill-Llama-70B   NousResearch/Hermes-3-Llama-3.1-70B   meta-llama/Llama-3.1-70B-Instruct
Model Size70b
Required VRAM140.2 GB
Updated2026-08-10
Maintainermlx-community
Model Typellama
Instruction-BasedYes
Model Files  5.0 GB: 1-of-28   5.1 GB: 2-of-28   5.1 GB: 3-of-28   5.1 GB: 4-of-28   5.1 GB: 5-of-28   5.1 GB: 6-of-28   5.1 GB: 7-of-28   5.1 GB: 8-of-28   5.1 GB: 9-of-28   5.1 GB: 10-of-28   5.1 GB: 11-of-28   5.1 GB: 12-of-28   5.1 GB: 13-of-28   5.1 GB: 14-of-28   5.1 GB: 15-of-28   5.1 GB: 16-of-28   5.1 GB: 17-of-28   5.1 GB: 18-of-28   5.1 GB: 19-of-28   5.1 GB: 20-of-28   5.1 GB: 21-of-28   5.1 GB: 22-of-28   5.1 GB: 23-of-28   5.1 GB: 24-of-28   5.1 GB: 25-of-28   5.1 GB: 26-of-28   5.1 GB: 27-of-28   2.6 GB: 28-of-28
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama3.1
Context Length131072
Model Max Length131072
Transformers Version5.5.1
Tokenizer ClassTokenizersBackend
Vocabulary Size128256

Best Alternatives to MIST 1 70B MLX

Best Alternatives
Context / RAM
Downloads
Likes
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB90695
... Chat 1048K Chinese Llama3 70B1024K / 141.9 GB76844
... 3 70B Instruct Gradient 1048K1024K / 141.9 GB22122
Llama3 Function Calling 1048K1024K / 141.9 GB51
...a 3 70B Instruct Gradient 524K512K / 141.9 GB2423
...a 3 70B Instruct Gradient 262K256K / 141.9 GB2056
...ama 3 70B Arimas Story RP V2.0256K / 141.1 GB103
...ama 3 70B Arimas Story RP V1.6256K / 141.2 GB50
...ama 3 70B Arimas Story RP V1.5256K / 141.2 GB213
Llama 3.1 70B Instruct128K / 141.9 GB813492938
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/MIST-1-70B-MLX.