What are the hardware requirements for LFM2 350M Unsloth Bnb 4bit?

LFM2 350M Unsloth Bnb 4bit requires approximately 0.3 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LFM2 350M Unsloth Bnb 4bit and how large is it?

LFM2 350M Unsloth Bnb 4bit is developed by unsloth, a model with 350m 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 LFM2 350M Unsloth Bnb 4bit?

LFM2 350M Unsloth Bnb 4bit is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LFM2 350M Unsloth Bnb 4bit by unsloth — VRAM 0.3GB, 32K context

Name: LFM2 350M Unsloth Bnb 4bit
Author: unsloth

LFM2 350M Unsloth Bnb 4bit is an open-source language model by unsloth. Features: 350m LLM, VRAM: 0.3GB, Context: 32K, License: other, Quantized, LLM Explorer Score: 0.2.

4-bit 4bit Ar Base model:liquidai/lfm2-350m Base model:quantized:liquidai/... Bitsandbytes Conversational De Edge En Endpoints compatible Es Fr Ja Ko Lfm2 Liquid Quantized Region:us Safetensors Unsloth Zh

Model Card on HF 🤗: https://huggingface.co/unsloth/LFM2-350M-unsloth-bnb-4bit

LFM2 350M Unsloth Bnb 4bit Parameters and Internals

LLM Name	LFM2 350M Unsloth Bnb 4bit
Repository 🤗	https://huggingface.co/unsloth/LFM2-350M-unsloth-bnb-4bit
Base Model(s)	LFM2 350M LiquidAI/LFM2-350M
Model Size	350m
Required VRAM	0.3 GB
Updated	2026-08-10
Maintainer	unsloth
Model Type	lfm2
Model Files	0.3 GB
Supported Languages	en ar zh fr de ja ko es
Quantization Type	4bit
Model Architecture	Lfm2ForCausalLM
License	other
Context Length	32768
Model Max Length	32768
Transformers Version	4.54.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|pad\|>
Vocabulary Size	65536
Torch Data Type	bfloat16

Rank the LFM2 350M Unsloth Bnb 4bit 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 LFM2 350M Unsloth Bnb 4bit

Best Alternatives	Context / RAM	Downloads	Likes
LFM2.5 350M MLX 8bit	125K / 0.4 GB	839	13
LFM2.5 350M MLX 4bit	125K / 0.2 GB	405	11
CHEETAH 350M Merged FP16	125K / 0.7 GB	13	0
LFM2.5 350M MLX 6bit	125K / 0.3 GB	108	10
LFM2.5 350M MLX 5bit	125K / 0.3 GB	98	8
...to Cleanup Lfm25 350M Mlx 5bit	125K / 0.2 GB	92	2
LFM2 350M 8bit	125K / 0.4 GB	423	4
LFM2 350M 4bit	125K / 0.2 GB	132	4
Claude Oss 350M	125K / 1.4 GB	841	8
LFM2.5 350M	125K / 0.7 GB	91807	384

Note: green Score (e.g. "73.2") means that the model is better than unsloth/LFM2-350M-unsloth-bnb-4bit.