What are the hardware requirements for LFM3 1.7B Base MLX 5bit?

LFM3 1.7B Base MLX 5bit requires approximately 1.2 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 Base MLX 5bit and how large is it?

LFM3 1.7B Base MLX 5bit is developed by alexwengg, 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 Base MLX 5bit?

LFM3 1.7B Base MLX 5bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM3 1.7B Base MLX 5bit by alexwengg — VRAM 1.2GB, 256K context

Name: LFM3 1.7B Base MLX 5bit
Author: alexwengg

LFM3 1.7B Base MLX 5bit is an open-source language model by alexwengg. Features: 1.7b LLM, VRAM: 1.2GB, Context: 256K, License: other, Quantized, LLM Explorer Score: 0.33.

5-bit 5bit Apple-silicon Ar Base-model Base model:liquidai/lfm3-1.7b-... Base model:quantized:liquidai/... Conversational Custom code De En Es Fr Hi Id It Ja Ko Lfm3 Liquid Mlx Pl Pt Quantized Region:us Ru Safetensors Th Vi Zh

Model Card on HF 🤗: https://huggingface.co/alexwengg/LFM3-1.7B-Base-MLX-5bit

LFM3 1.7B Base MLX 5bit Parameters and Internals

LLM Name	LFM3 1.7B Base MLX 5bit
Repository 🤗	https://huggingface.co/alexwengg/LFM3-1.7B-Base-MLX-5bit
Base Model(s)	LiquidAI/LFM3-1.7B-Base LiquidAI/LFM3-1.7B-Base
Model Size	1.7b
Required VRAM	1.2 GB
Updated	2026-10-31
Maintainer	alexwengg
Model Type	lfm3
Model Files	1.2 GB
Supported Languages	en ar zh fr de it ja ko pt es vi th id hi ru pl
Quantization Type	5bit
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 Base MLX 5bit 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 Base MLX 5bit

Best Alternatives	Context / RAM	Downloads	Likes
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 OptiQ 4bit	256K / 1.3 GB	430	1
LFM3 1.7B Frontier SmartAgent	512K / 1.1 GB	1824	2
LFM3 1.7B	256K / 3.5 GB	32933	624
LFM3 1.7B Base	256K / 3.5 GB	3152	93
LFM3 1.7B MLX Bf16	256K / 3.5 GB	1385	11
LFM3 1.7B NVFP4	256K / 1.8 GB	1360	16

Note: green Score (e.g. "73.2") means that the model is better than alexwengg/LFM3-1.7B-Base-MLX-5bit.