selfhost.directory

The index of self-hostable projects — ranked, categorized and served with live updates.
Own your data and stop giving it to big tech.

LFM3-1.7B-Base

Side-by-side specs, memory needs, licence, runtimes and benchmarks. Add up to 4 models.

--vram
any
--gpus
--quant
--add

On your GPU

  • LFM3-1.7B-Base
Property
Overview
TaskChat
Parameters1.7B
Active parametersdense
Context length256K
Input → output
Released26 Oct 2026
Licencelfm1.0
Gated downloadno
Memory and speed
Fits your hardwarepick a GPU above≈1.9 GB
VRAM at Q4≈1.9 GB
VRAM at Q8≈2.7 GB
VRAM at FP16≈4.3 GB
Est. generation speedpick a GPU above—
Popularity
Downloads / 30 days11K
Likes160
Runs with
llama.cpp
Ollama
Transformers
Ollama taglfm3:1.7b
Architecture
ArchitectureLfm3ForCausalLM
Layers24
Attention / KV heads16 / 4
Vocabulary128 000
Weights dtypebfloat16
GGUF availableyes

Keep comparing

Memory figures are estimates for an 8K context at the chosen quantisation (Q4_K_M for LLMs by default). Speeds are rough, memory-bound estimates. Self-reported benchmark scores come from the model authors.