FinnAI SLM v4 β€” LiteRT-LM (on-device)

Ready-to-run INT4 package of finndot/finnai-slm-v4 for Android / LiteRT-LM.

Use this when you want FinnAI on a phone: parse Indian bank SMS and answer short finance questions on-device.

File Notes
qwen3_1.7b_finndot_nothink_q4_ekv1280.litertlm INT4, KV 1280, thinking off Β· 973,979,088 bytes

SHA256: 36e5ec021730f0e060b78c2371d1e0011c34f28c407cdf9f993232b5cd87e7c0

FinnAI model family

Version Weights On-device LiteRT
v4 (this) finnai-slm-v4 finnai-slm-v4-litertlm
v3 finnai-slm-v3 finnai-slm-v3-litertlm
v2 finnai-slm-v2 β€”

Download

huggingface-cli download finndot/finnai-slm-v4-litertlm \
  qwen3_1.7b_finndot_nothink_q4_ekv1280.litertlm \
  --local-dir .

Used by FinnDot. Full bf16 / Transformers weights: finndot/finnai-slm-v4.

License

Apache 2.0

Downloads last month
30
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for finndot/finnai-slm-v4-litertlm

Finetuned
Qwen/Qwen3-1.7B
Finetuned
(2)
this model