What are the hardware requirements for Qwen3.8 9B Mlx 4Bit?

Qwen3.8 9B Mlx 4Bit requires approximately 5 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.8 9B Mlx 4Bit and how large is it?

Qwen3.8 9B Mlx 4Bit is developed by keXjos, a model with 9b 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 Qwen3.8 9B Mlx 4Bit?

Qwen3.8 9B Mlx 4Bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.8 9B Mlx 4Bit by keXjos — VRAM 5GB

Name: Qwen3.8 9B Mlx 4Bit
Author: keXjos

Qwen3.8 9B Mlx 4Bit is an open-source language model by keXjos. Features: 9b LLM, VRAM: 5GB, License: apache-2.0, Quantized.

4-bit 4bit Base model:empero-ai/qwen3.8-9... Base model:quantized:empero-ai... Conversational Distillation Empero-ai En Endpoints compatible Function-calling Image-text-to-text Mlx Mlx-my-repo Quantized Qwen3.5 Qwen3.8 Qwen3 5 Reasoning Region:us Safetensors Sft

Model Card on HF 🤗: https://huggingface.co/keXjos/Qwen3.8-9B-mlx-4Bit

Qwen3.8 9B Mlx 4Bit Parameters and Internals

LLM Name	Qwen3.8 9B Mlx 4Bit
Repository 🤗	https://huggingface.co/keXjos/Qwen3.8-9B-mlx-4Bit
Base Model(s)	empero-ai/Qwen3.8-9B empero-ai/Qwen3.8-9B
Model Size	9b
Required VRAM	5 GB
Updated	2026-08-17
Maintainer	keXjos
Model Type	qwen3_5
Model Files	5.0 GB
Supported Languages	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 Qwen3.8 9B 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 Qwen3.8 9B Mlx 4Bit

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 9B MLX 4bit	0K / 5.9 GB	580012	4
Qwen3.5 9B MLX 8bit	0K / 10.4 GB	550497	1
Ornith 1.0 9B 4bit	0K / 5.9 GB	9791	9
Qwen3.5 9B MLX 4bit	0K / 5.9 GB	22827	151
Ornith 1.0 9B OptiQ 4bit	0K / 7.1 GB	1656	8
Qwen3.5 9B 8bit	0K / 10.4 GB	45652	17
Qwen3.5 9B OptiQ 4bit	0K / 7.1 GB	10136	86
Ornith 1.0 9B 8bit	0K / 10.4 GB	2079	2
Qwen3.5 9B 4bit	0K / 5.9 GB	17566	12
Ornith 1.0 9B OptiQ 6bit	0K / 8.1 GB	125	1

Note: green Score (e.g. "73.2") means that the model is better than keXjos/Qwen3.8-9B-mlx-4Bit.