LLM EXPLORER 63,791 MODELS INDEXED

JEV 27B VL MLX 8bit by nativ-community

By nativ-community · 252 downloads
HF Repo ↗ Copy URL

JEV 27B VL MLX 8bit is an open-source language model by nativ-community. Features: 27b LLM, VRAM: 30.5GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.32.

  8-bit   8bit Base model:autotrust/jev-27b-v... Base model:quantized:autotrust...   Conversational   Decision-model   Image-text-to-text   Jev   Mlx   Mlx-vlm   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/nativ-community/JEV-27B-VL-MLX-8bit 

JEV 27B VL MLX 8bit Parameters and Internals

LLM NameJEV 27B VL MLX 8bit
Repository 🤗https://huggingface.co/nativ-community/JEV-27B-VL-MLX-8bit 
Base Model(s)  JEV 27B VL   autotrust/JEV-27B-VL
Model Size27b
Required VRAM30.5 GB
Updated2026-10-11
Maintainernativ-community
Model Typejev
Model Files  5.3 GB: 1-of-6   5.3 GB: 2-of-6   5.3 GB: 3-of-6   5.3 GB: 4-of-6   5.3 GB: 5-of-6   4.0 GB: 6-of-6
Quantization Type8bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.8.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to JEV 27B VL MLX 8bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.6 27B OptiQ 4bit256K / 18.7 GB1306559
Bonsai 27B Mlx 1bit0K / 5.1 GB809309205
Ternary Bonsai 27B Mlx 2bit0K / 8.5 GB809024168
Qwen3.8 27B MLX 5bit0K / 19.5 GB46750442
Qwen3.6 27B MLX 8bit0K / 29.4 GB87914514
Qwen3.6 27B MLX 6bit0K / 22.7 GB8129772
Qwen3.6 27B MLX 4bit0K / 16 GB84686116
JEV 27B VL MLX 4bit0K / 16 GB6675
Qwen3.8 27B 8bit0K / 29.4 GB1389233
...onsai 2 27B CRACK Ternary JANG0K / 8.1 GB268913
Note: green Score (e.g. "73.2") means that the model is better than nativ-community/JEV-27B-VL-MLX-8bit.