LLM EXPLORER 66,845 MODELS INDEXED

Jev Style Qwen3.5 2B Decision MLX Bf16 by chaoliangUNSW

By chaoliangUNSW · 2801 downloads
HF Repo ↗ Copy URL

Jev Style Qwen3.5 2B Decision MLX Bf16 is an open-source language model by chaoliangUNSW. Features: 2b LLM, VRAM: 3.8GB, License: apache-2.0, LLM Explorer Score: 0.3.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-2b-bas...   Calibration   Classification   Conversational   Dataset:fancyzhx/ag news   Dataset:google/boolq   Dataset:nyu-mll/glue   Dataset:setfit/sst5   Decision-model   En   Jev-style   Mlx   Qwen3.5   Qwen3 5   Region:us   Safetensors   System-one
Model Card on HF 🤗: https://huggingface.co/chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-MLX-bf16 

Jev Style Qwen3.5 2B Decision MLX Bf16 Parameters and Internals

LLM NameJev Style Qwen3.5 2B Decision MLX Bf16
Repository 🤗https://huggingface.co/chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-MLX-bf16 
Base Model(s)  Qwen/Qwen3.5-2B-Base   Qwen/Qwen3.5-2B-Base
Model Size2b
Required VRAM3.8 GB
Updated2026-09-24
MaintainerchaoliangUNSW
Model Typeqwen3_5
Model Files  3.8 GB
Supported Languagesen
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Jev Style Qwen3.5 2B Decision MLX Bf16

Best Alternatives
Context / RAM
Downloads
Likes
MiniCPM OCR Jev0K / 4.4 GB177080
Qwen3.5 2B0K / 4.5 GB2633311352
RynnBrain1.1 2B0K / 4.4 GB26857912
Index Translate 2B0K / 4.5 GB208965
Qwen3.5 2B Base0K / 4.5 GB80959182
WeMM Embedding 2B0K / 5.4 GB543368
Qwen3.8 2B Distill Heretic V20K / 4.4 GB8362
Qwen3.5 2B0K / 4.5 GB10348718
GLiDE 2B0K / 3.8 GB1094
Qwen3.8 2B Distill0K / 4.5 GB205624
Note: green Score (e.g. "73.2") means that the model is better than chaoliangUNSW/Jev-Style-Qwen3.5-2B-Decision-MLX-bf16.