LLM EXPLORER 61,755 MODELS INDEXED

Mavery Lehrling 0.8B MLX 4bit by rhymeas

By rhymeas · 77 downloads
HF Repo ↗ Copy URL

Mavery Lehrling 0.8B MLX 4bit is an open-source language model by rhymeas. Features: 0.8b LLM, VRAM: 0.4GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

  4-bit   4bit   Apple-silicon Base model:quantized:qwen/qwen...   Base model:qwen/qwen3.5-0.8b   Conversational   De   Dictation   En   Mlx   Punctuation   Quantized   Qwen3 5   Region:us   Safetensors   Text-cleanup   Text-normalization   Truecasing
Model Card on HF 🤗: https://huggingface.co/rhymeas/Mavery-Lehrling-0.8B-MLX-4bit 

Mavery Lehrling 0.8B MLX 4bit Parameters and Internals

LLM NameMavery Lehrling 0.8B MLX 4bit
Repository 🤗https://huggingface.co/rhymeas/Mavery-Lehrling-0.8B-MLX-4bit 
Base Model(s)  Qwen/Qwen3.5-0.8B   Qwen/Qwen3.5-0.8B
Model Size0.8b
Required VRAM0.4 GB
Updated2026-09-20
Maintainerrhymeas
Model Typeqwen3_5
Model Files  0.4 GB
Supported Languagesde en
Quantization Type4bit
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version4.57.0.dev0
Tokenizer ClassTokenizersBackend
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to Mavery Lehrling 0.8B MLX 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Qwen3.5 0.8B MLX 4bit0K / 0.6 GB51135
Qwen3.5 0.8B 8bit0K / 1 GB47922
Qwen3.5 0.8B 4bit0K / 0.6 GB25493
Qwen3.5 0.8B OptiQ 4bit0K / 0.2 GB149422
Chartreader 0.8B OptiQ 4bit0K / 0.7 GB1052
OvisOCR20K / 1.7 GB124131463
Qwen3.5 0.8B0K / 1.8 GB2839884655
Qwen3.5 0.8B Base0K / 1.8 GB82805492
...iptagent Qwen35 0.8B V2 Merged0K / 3.4 GB3673
Qwen3.5 0.8B0K / 1.8 GB4766319
Note: green Score (e.g. "73.2") means that the model is better than rhymeas/Mavery-Lehrling-0.8B-MLX-4bit.