LLM EXPLORER 56,604 MODELS INDEXED

LFM2.5 1.2B Instruct MLX 5bit by LiquidAI

By LiquidAI · 91 downloads
HF Repo ↗ Copy URL

LFM2.5 1.2B Instruct MLX 5bit is an open-source language model by LiquidAI. Features: 1.2b LLM, VRAM: 0.8GB, Context: 125K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.22.

  5-bit   5bit   Ar Base model:liquidai/lfm2.5-1.2... Base model:quantized:liquidai/...   Conversational   De   Edge   En   Es   Fr   Instruct   It   Ja   Ko   Lfm2   Lfm2.5   Liquid   Mlx   Pt   Quantized   Region:us   Safetensors   Zh
Model Card on HF 🤗: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-MLX-5bit 

LFM2.5 1.2B Instruct MLX 5bit Parameters and Internals

LLM NameLFM2.5 1.2B Instruct MLX 5bit
Repository 🤗https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-MLX-5bit 
Base Model(s)  LiquidAI/LFM2.5-1.2B-Instruct   LiquidAI/LFM2.5-1.2B-Instruct
Model Size1.2b
Required VRAM0.8 GB
Updated2026-08-08
MaintainerLiquidAI
Model Typelfm2
Instruction-BasedYes
Model Files  0.8 GB
Supported Languagesen ja ko fr es de it pt ar zh
Quantization Type5bit
Model ArchitectureLfm2ForCausalLM
Licenseother
Context Length128000
Model Max Length128000
Transformers Version4.57.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|pad|>
Vocabulary Size65536

Best Alternatives to LFM2.5 1.2B Instruct MLX 5bit

Best Alternatives
Context / RAM
Downloads
Likes
LFM2.5 1.2B Instruct 4bit125K / 0.7 GB150151
LFM2.5 1.2B Instruct MLX 8bit125K / 1.2 GB68125
LFM2.5 1.2B Instruct MLX 6bit125K / 1 GB9410
...1.2B Instruct Abliterated 6bit125K / 1 GB251
LFM2.5 1.2B Instruct125K / 2.3 GB575331647
LFM2.5 1.2B Instruct125K / 2.3 GB226738
Lfm2.5 1.2B Noval Agentic125K / 2.3 GB840
Lfm2.5 1.2B Asterion Agentic125K / 2.3 GB530
...B SFT Claude Reasoning Unsloth125K / 2.3 GB4920
...1.2B Noval Instruct Paramdelta125K / 2.3 GB430
Note: green Score (e.g. "73.2") means that the model is better than LiquidAI/LFM2.5-1.2B-Instruct-MLX-5bit.