What are the hardware requirements for Mavery Geselle 2B MLX 4bit?

Mavery Geselle 2B MLX 4bit requires approximately 1.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Mavery Geselle 2B MLX 4bit and how large is it?

Mavery Geselle 2B MLX 4bit is developed by rhymeas, a model with 2b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Mavery Geselle 2B MLX 4bit?

Mavery Geselle 2B MLX 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Mavery Geselle 2B MLX 4bit by rhymeas — VRAM 1.7GB

Name: Mavery Geselle 2B MLX 4bit
Author: rhymeas

Mavery Geselle 2B MLX 4bit is an open-source language model by rhymeas. Features: 2b LLM, VRAM: 1.7GB, License: apache-2.0, Quantized, LLM Explorer Score: 0.3.

4-bit 4bit Apple-silicon Base model:quantized:qwen/qwen... Base model:qwen/qwen3.5-2b 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-Geselle-2B-MLX-4bit

Mavery Geselle 2B MLX 4bit Parameters and Internals

LLM Name	Mavery Geselle 2B MLX 4bit
Repository 🤗	https://huggingface.co/rhymeas/Mavery-Geselle-2B-MLX-4bit
Base Model(s)	Qwen/Qwen3.5-2B Qwen/Qwen3.5-2B
Model Size	2b
Required VRAM	1.7 GB
Updated	2026-09-20
Maintainer	rhymeas
Model Type	qwen3_5
Model Files	1.7 GB
Supported Languages	de en
Quantization Type	4bit
Model Architecture	Qwen3_5ForConditionalGeneration
License	apache-2.0
Model Max Length	262144
Transformers Version	4.57.0.dev0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Mavery Geselle 2B MLX 4bit capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Mavery Geselle 2B MLX 4bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.8 2B Distill Mlx 5Bit	0K / 1.3 GB	387	1
Qwen3.5 2B MLX 4bit	0K / 1.7 GB	12310	2
Qwen3.5 2B 6bit	0K / 2.2 GB	8680	7
Qwen3.5 2B 4bit	0K / 1.7 GB	5374	5
Qwen3.5 2B OptiQ 4bit	0K / 0.7 GB	1296	12
Spartan 1.2 2B MLX 8bit	0K / 1.1 GB	27	0
Qwen3.5 2B 8bit	0K / 2.7 GB	202	1
Qwen3.5 2B	0K / 4.5 GB	2633311	352
WeMM Embedding 2B	0K / 5.4 GB	5433	68
Qwen3.5 2B Base	0K / 4.5 GB	809591	82

Note: green Score (e.g. "73.2") means that the model is better than rhymeas/Mavery-Geselle-2B-MLX-4bit.