lfm3:1.7b-mlx-bf16

129 3 hours ago

LFM3-1.7B is a tri-hybrid model for local agents and specialized applications.

tools thinking 1.7b 
ollama run lfm3:1.7b-mlx-bf16

Details

3 hours ago

f39cc56813fb ยท 3.5GB

json
{ "_from_model_config": true, "bos_token_id": 124894, "eos_token_id": [ 124900 ], "output_attentions
json
{ "bos_token": "<|startoftext|>", "eos_token": "<|im_end|>", "pad_token": "<|pad|>" }
json
{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 124893, "content"
json
{ "audio_out_token": "<|audio_out|>", "audio_token": "<|audio|>", "backend": "tokenizers", "bos_toke
license
LFM Open License v1.0 TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 1. Definitions. "
params
{ "repeat_last_n": -1, "repeat_penalty": 1.1, "temperature": 0.1, "top_k": 50, "
json
{ "architectures": [ "Lfm3ForCausalLM" ], "auto_map": { "AutoConfig": "configuration_lfm3.Lfm3Config
286 tensors

Readme

LFM3-1.7B is a text model for local agents and specialized applications, based on a new tri-hybrid architecture.

  • Agentic training: post-trained for agentic harnesses such as Hermes Agent, Pi, and OpenClaw, with a 256K-token context window.
  • Designed for the edge: at 4-bit precision, it takes about 1 GB of memory, so it fits on any phone or laptop.
  • Made to be specialized: adapt the model to your domains, formats, and tools via quick single-GPU fine-tuning.

Model details

The LFM3 family includes base, text, vision, audio, omni, and decision models.

Property Specification
Checkpoint Post-trained, text-only language model
Parameters 1.73B
Architecture 24 layers: 13 gated short convolutions, 5 sliding-window attention, 6 global attention
Context length 256K tokens (input + output)
Vocabulary 128,000 tokens
Languages English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish
License LFM Open License v1.0

LFM3-1.7B is designed for local agents, tool calling, structured outputs, and domain-specific fine-tuning. Use retrieval or search for knowledge-heavy tasks. It is not recommended for agentic coding or complex multi-step reasoning due to its small size.