LLM EXPLORER 61,491 MODELS INDEXED

Qwen2.5 7B Instruct 1M 6bit by mlx-community

By mlx-community · 52 downloads
HF Repo ↗ Copy URL

Qwen2.5 7B Instruct 1M 6bit is an open-source language model by mlx-community. Features: 7b LLM, VRAM: 6.2GB, Context: 986K, License: apache-2.0, Quantized, Instruction-Based, LLM Explorer Score: 0.16.

  6-bit   6bit Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-7b-ins...   Chat   Conversational   En   Endpoints compatible   Instruct   Mlx   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen2.5-7B-Instruct-1M-6bit 

Qwen2.5 7B Instruct 1M 6bit Parameters and Internals

LLM NameQwen2.5 7B Instruct 1M 6bit
Repository 🤗https://huggingface.co/mlx-community/Qwen2.5-7B-Instruct-1M-6bit 
Base Model(s)  Qwen/Qwen2.5-7B-Instruct-1M   Qwen/Qwen2.5-7B-Instruct-1M
Model Size7b
Required VRAM6.2 GB
Updated2026-05-27
Maintainermlx-community
Model Typeqwen2
Instruction-BasedYes
Model Files  5.4 GB: 1-of-2   0.8 GB: 2-of-2
Supported Languagesen
Quantization Type6bit
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length1010000
Model Max Length1010000
Transformers Version4.47.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 7B Instruct 1M 6bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB44411
...wen2.5 7B Instruct 1M Bnb 4bit986K / 5.5 GB2671
Qwen2.5 7B Instruct 1M 8bit986K / 8.1 GB634
...B Instruct 1M Unsloth Bnb 4bit986K / 7.5 GB373
Alisia 7B Instruct V1128K / 15.4 GB1142
...5 7B Instruct SFT Meme LoRA V7128K / 15.2 GB60
Gte Qwen2 7B Instruct 4bit DWQ128K / 4.3 GB883
Grok Demon 7b32K / 15.2 GB8521
Qwen2.5 7B Security Cot32K / 15.2 GB3642
Huginn Cs Tutor V132K / 15.2 GB2761
Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen2.5-7B-Instruct-1M-6bit.