What are the hardware requirements for Fuse 1 Lite MLX?

Fuse 1 Lite MLX requires approximately 11.4 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Fuse 1 Lite MLX and how large is it?

Fuse 1 Lite MLX is developed by Akahsizrr, a model with 35b 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 Fuse 1 Lite MLX?

Fuse 1 Lite MLX is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Fuse 1 Lite MLX by Akahsizrr — VRAM 11.4GB, 128K context

Name: Fuse 1 Lite MLX
Author: Akahsizrr

Fuse 1 Lite MLX is an open-source language model by Akahsizrr. Features: 35b LLM, VRAM: 11.4GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.33.

Apple-silicon Base model:akahsizrr/fuse-1-li... Base model:finetune:akahsizrr/... Coding Conversational En Fuse3 Lfm2 Mixture-of-experts Mlx Moe Qwen Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/Akahsizrr/fuse-1-Lite-MLX

Fuse 1 Lite MLX Parameters and Internals

LLM Name	Fuse 1 Lite MLX
Repository 🤗	https://huggingface.co/Akahsizrr/fuse-1-Lite-MLX
Base Model(s)	Fuse 1 Lite LiquidAI/LFM2.5-2.6B Qwen/Qwen3.6-35B-A3B Akahsizrr/fuse-1-Lite LiquidAI/LFM2.5-2.6B Qwen/Qwen3.6-35B-A3B
Model Size	35b
Required VRAM	11.4 GB
Updated	2026-08-09
Maintainer	Akahsizrr
Model Type	fuse3
Model Files	11.4 GB
Supported Languages	en
Model Architecture	Fuse3ForCausalLM
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	5.14.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the Fuse 1 Lite MLX 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 Fuse 1 Lite MLX

Best Alternatives	Context / RAM	Downloads	Likes
Fuse 1 Lite	128K / 11.4 GB	309	81

Note: green Score (e.g. "73.2") means that the model is better than Akahsizrr/fuse-1-Lite-MLX.