What are the hardware requirements for LFM3 1.7B FP8?

LFM3 1.7B FP8 requires approximately 2.2 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 LFM3 1.7B FP8 and how large is it?

LFM3 1.7B FP8 is developed by LiquidAI, 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 LFM3 1.7B FP8?

LFM3 1.7B FP8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM3 1.7B FP8 by LiquidAI — VRAM 2.2GB, 256K context

Name: LFM3 1.7B FP8
Author: LiquidAI

LFM3 1.7B FP8 is an open-source language model by LiquidAI. Features: 1.7b LLM, VRAM: 2.2GB, Context: 256K, License: other, LLM Explorer Score: 0.36.

Base model:liquidai/lfm3-1.7b Base model:quantized:liquidai/... Compressed-tensors Conversational Custom code Fp8 Lfm3 Liquid Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM3-1.7B-FP8

LFM3 1.7B FP8 Parameters and Internals

LLM Name	LFM3 1.7B FP8
Repository 🤗	https://huggingface.co/LiquidAI/LFM3-1.7B-FP8
Base Model(s)	LiquidAI/LFM3-1.7B LiquidAI/LFM3-1.7B
Model Size	1.7b
Required VRAM	2.2 GB
Updated	2026-10-30
Maintainer	LiquidAI
Model Type	lfm3
Model Files	2.2 GB
Model Architecture	Lfm3ForCausalLM
License	other
Context Length	262144
Model Max Length	262144
Transformers Version	5.12.1
Tokenizer Class	TokenizersBackend
Padding Token	<\|pad\|>
Vocabulary Size	128000

Rank the LFM3 1.7B FP8 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 LFM3 1.7B FP8

Best Alternatives	Context / RAM	Downloads	Likes
LFM3 1.7B MLX Bf16	256K / 3.5 GB	1385	11
LFM3 1.7B NVFP4	256K / 1.8 GB	1360	16
LFM3 1.7B ONNX	256K / GB	932	13
LFM3 1.7B MLX 4bit	256K / 1 GB	4944	16
LFM3 1.7B MLX 8bit	256K / 1.8 GB	2348	11
LFM3 1.7B MLX 6bit	256K / 1.4 GB	407	9
LFM3 1.7B MLX 5bit	256K / 1.2 GB	429	7
LFM3 1.7B Heretic Abliterated	256K / 3.5 GB	297	2
EchoPulse 1.7B	256K / 1.1 GB	75	0

Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM3-1.7B-FP8.