LLM EXPLORER 58,608 MODELS INDEXED

Qwen3.5 4B Qat Lean 4bit Mlx by YoozLabs

By YoozLabs · 155 downloads
HF Repo ↗ Copy URL

Qwen3.5 4B Qat Lean 4bit Mlx is an open-source language model by YoozLabs. Features: 4b LLM, VRAM: 2.4GB, Context: 256K, License: apache-2.0, Quantized, LLM Explorer Score: 0.27.

  4-bit   4bit Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.5-4b   Conversational   Lean-qat-mlx   Mlx   Qat   Quantized   Qwen3.5   Qwen3 5   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx 

Qwen3.5 4B Qat Lean 4bit Mlx Parameters and Internals

LLM NameQwen3.5 4B Qat Lean 4bit Mlx
Repository 🤗https://huggingface.co/YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx 
Base Model(s)  Qwen/Qwen3.5-4B   Qwen/Qwen3.5-4B
Model Size4b
Required VRAM2.4 GB
Updated2026-07-27
MaintainerYoozLabs
Model Typeqwen3_5
Model Files  2.4 GB
Quantization Type4bit
Model ArchitectureQwen3_5ForCausalLM
Licenseapache-2.0
Context Length262144
Model Max Length262144
Transformers Version5.13.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size248320
Errorsreplace

Best Alternatives to Qwen3.5 4B Qat Lean 4bit Mlx

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 4B Code Forged256K / 8.4 GB1721
Agents A1 4B Fable Preview256K / 8.4 GB1030
...ts A1 4B Fable Preview Heretic256K / 8.4 GB22852
Qwen35 4B T13 Opd Rkl Ckpt50256K / 8.4 GB4670
Zira Researcher256K / 8.4 GB1525012
...nts A1 4B Kimi Preview Heretic256K / 8.4 GB2870
Qwen3.5 4B EU256K / 9.7 GB870
Qwen3.5 4B INT8256K / 4.8 GB3492
Qwen35 4B Soyuz Merged256K / 8.4 GB1903
Retrico Lm 4B Finetuned V4256K / 0 GB1430
Note: green Score (e.g. "73.2") means that the model is better than YoozLabs/Qwen3.5-4B-qat-lean-4bit-mlx.