What are the hardware requirements for Diffusion LFM3 1.7B Pre?

Diffusion LFM3 1.7B Pre requires approximately 3.5 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Diffusion LFM3 1.7B Pre and how large is it?

Diffusion LFM3 1.7B Pre is developed by summerAIO, 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 Diffusion LFM3 1.7B Pre?

Diffusion LFM3 1.7B Pre is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Diffusion LFM3 1.7B Pre by summerAIO — VRAM 3.5GB, 256K context

Name: Diffusion LFM3 1.7B Pre
Author: summerAIO

Diffusion LFM3 1.7B Pre is an open-source language model by summerAIO. Features: 1.7b LLM, VRAM: 3.5GB, Context: 256K, License: other.

Base model:finetune:liquidai/l... Base model:liquidai/lfm3-1.7b-... Block-diffusion Conversational Custom code Diffusion-language-model Endpoints compatible Lfm3 Masked-diffusion Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/summerAIO/Diffusion-LFM3-1.7B-pre

Diffusion LFM3 1.7B Pre Parameters and Internals

LLM Name	Diffusion LFM3 1.7B Pre
Repository 🤗	https://huggingface.co/summerAIO/Diffusion-LFM3-1.7B-pre
Base Model(s)	LiquidAI/LFM3-1.7B-Base LiquidAI/LFM3-1.7B-Base
Model Size	1.7b
Required VRAM	3.5 GB
Updated	2026-11-14
Maintainer	summerAIO
Model Type	lfm3
Model Files	2.0 GB: 1-of-2 1.5 GB: 2-of-2
Model Architecture	Lfm3ForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	5.22.2
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	125034

Rank the Diffusion LFM3 1.7B Pre 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 Diffusion LFM3 1.7B Pre

Best Alternatives	Context / RAM	Downloads	Likes
LFM3 1.7B	256K / 3.5 GB	32933	624
LFM3 1.7B Base	256K / 3.5 GB	3152	93
LFM3 1.7B NVFP4	256K / 1.8 GB	1360	16
LFM3 1.7B MLX Bf16	256K / 3.5 GB	1385	11
LFM3 1.7B ONNX	256K / GB	932	13
LFM3 1.7B FP8	256K / 2.2 GB	893	12
Himel3 1.7B	256K / 3.5 GB	485	1
Himel3 1.7B Graft	256K / 3.5 GB	476	1
LFM3 1.7B DERISKED	256K / 3.5 GB	85	11
...3 1.7B Claude Code Safetensors	256K / 3.5 GB	975	1

Note: green Score (e.g. "73.2") means that the model is better than summerAIO/Diffusion-LFM3-1.7B-pre.