LocalClaw/LLM/IbnSina-1.5B
Open-weight local LLM

IbnSina-1.5B

Catalogue summary: IbnSina-1.5B is a Persian-first 1.48B Llama-compatible language model trained from scratch on a Persian-heavy corpus, with Apache 2.0 weights and GGUF artifacts for laptop, phone, Ollama, LM Studio and llama.cpp use.

Repository editorial metadata; verify comparative claims in the linked upstream material.

4 GB catalogue minimum4 GB RAMQ4_K_MFast chat
Choose an app

Pick the app you already use. No terminal and no command to copy.

Compare models
Open in LM StudioOpens the app on this model's download screenOpen in UnslothLaunches Unsloth Desktop on this model's download page
OllamaNot available for this model
Open on Hugging FaceFiles, licence and available downloadsOpen llama.cpp setupAdvanced option: opens the model filesUse with LocalClawOptional workspace after the model is installed

Desktop app links require the app to be installed. If nothing opens, LocalClaw will show app-download and model-file fallbacks.

Parameters
1.5B
Minimum RAM
4 GB
Model size
0.9 GB
Quantization
Q4_K_M

Can IbnSina-1.5B run locally?

IbnSina-1.5B has a catalogue minimum of 4 GB RAM with Q4_K_M. Actual memory use and speed vary by context length, runtime, backend and system headroom.

Use ibnsina-1.5b as the catalogue search term in a compatible runtime, and confirm the available format on the upstream repository before download.

Model sourcePublic GGUF repository (verified 2026-09-07): ibnsina-llm/ibnsina-1.5bUpstream releasePaper or model cardLicence text
chatlightspeedmultilingualgeneral

Install path

01
Check RAM fitMinimum 4 GB RAM. Start with the Q4_K_M quant.
02
Load the modelSearch ibnsina-1.5b in LM Studio.
03
Control locallyUse LocalClaw to manage models, agents, chat, channels and scheduled OpenClaw work.

Catalogue record

  • Family: ibnsina
  • Parameters: 1.5B
  • Recommended quantization: Q4_K_M
  • Catalogue minimum RAM: 4 GB
  • Catalogue model size: 0.9 GB
  • Tags: chat, light, speed, multilingual, general

Practical limits

  • Catalogue RAM is a minimum estimate, not a guarantee for every context length or runtime.
  • Speed and memory use vary by quantization, backend, context length and system headroom.
  • Verify architecture, licence and usage restrictions in the linked upstream material before deployment.

Catalogue tags

  • chat
  • light
  • speed
  • multilingual
  • general

Capability profile

Repository catalogue ratings used by LocalClaw's editorial rubric. They are not a standardized third-party benchmark.

speed
10
quality
5
coding
2
reasoning
4

Technical notes

Developer
IbnSina LLM
License
Apache 2.0
Context window
2,048 tokens
Architecture
Llama-compatible dense 1.48B language model with 28 layers, 2048 hidden size, grouped-query attention, SwiGLU feed-forward blocks, RMSNorm and a Persian-dominant byte-level BPE tokenizer.

This model fits these next steps

Hardware fit is based on LocalClaw's RAM tier, model size and quantization metadata. Always leave memory headroom for your OS and runtime.

Entry laptop fitMacBook Air 8GBMore headroomMac mini M4 16GBAll compatible picks8GB RAM guide

Related catalogue entries

Linked mechanically by family, shared tags and nearby RAM tier; this is not a quality ranking.

DFM-Mimir 1.8BGranite 4.1 (3B) 3BLlama 3.2 (1B) 1BLlama 3.2 (3B) 3BMiniCPM5 1B 1BMinistral 3 3B Instruct 3BLFM2.5-2.6B 2.7BLing-3.0-tiny 7.9B (1.3B active, MoE)

Where to go next