What are the hardware requirements for Qwen3 1.7B MLX MXFP4?

Qwen3 1.7B MLX MXFP4 requires approximately 0.9 GB of VRAM and supports a context window of 40K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3 1.7B MLX MXFP4 and how large is it?

Qwen3 1.7B MLX MXFP4 is developed by mlx-community, a model with 1.7b 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 1.7B MLX MXFP4?

Qwen3 1.7B MLX MXFP4 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3 1.7B MLX MXFP4 by mlx-community — VRAM 0.9GB, 40K context

Name: Qwen3 1.7B MLX MXFP4
Author: mlx-community

Qwen3 1.7B MLX MXFP4 is an open-source language model by mlx-community. Features: 1.7b LLM, VRAM: 0.9GB, Context: 40K, License: apache-2.0, LLM Explorer Score: 0.2.

4-bit Base model:quantized:qwen/qwen... Base model:qwen/qwen3-1.7b Conversational Mlx Qwen3 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/mlx-community/Qwen3-1.7B-MLX-MXFP4

Qwen3 1.7B MLX MXFP4 Parameters and Internals

LLM Name	Qwen3 1.7B MLX MXFP4
Repository 🤗	https://huggingface.co/mlx-community/Qwen3-1.7B-MLX-MXFP4
Base Model(s)	Qwen/Qwen3-1.7B Qwen/Qwen3-1.7B
Model Size	1.7b
Required VRAM	0.9 GB
Updated	2026-07-22
Maintainer	mlx-community
Model Type	qwen3
Model Files	0.9 GB
Model Architecture	Qwen3ForCausalLM
License	apache-2.0
Context Length	40960
Model Max Length	40960
Transformers Version	4.51.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Torch Data Type	bfloat16
Errors	replace

Rank the Qwen3 1.7B MLX MXFP4 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 1.7B MLX MXFP4

Best Alternatives	Context / RAM	Downloads	Likes
Lucy 128K	128K / 3.4 GB	123	112
Polaris 1.7B Preview	128K / 3.4 GB	73	8
DictaLM 3.0 1.7B Instruct	60K / 3.4 GB	2842	1
Qwen3 1.7B	40K / 4 GB	5633291	500
CORe Pico 4	40K / 3.4 GB	895	2
CORe Pico V3	40K / 3.4 GB	720	0
...en3 1.7B Teacher Note Severity	40K / 3.4 GB	386	0
KBevo Qwen3 1.7B SFT	40K / 3.4 GB	462	0
Qwen3 1.7B ONNX Web	40K / GB	178	1
RIFA FLASH 1.7B	40K / 3.4 GB	583	0

Note: green Score (e.g. "73.2") means that the model is better than mlx-community/Qwen3-1.7B-MLX-MXFP4.